© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 152
    Prev
    Next
    INDEX
    Explanations

    legal terms and references related to court procedures and costs.

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    legal terms and phrases associated with court cases and fees.

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    legal statute and case citations, particularly those involving numbered sections and subsections.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @bot

    legal sections

    np_acts-logits-general · gemini-2.0-flash

    section numbers (n)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     कैसी
    -0.49
    omock
    -0.48
    hael
    -0.48
    migrationBuilder
    -0.46
    omitempty
    -0.46
    HostException
    -0.45
     MaterialApp
    -0.45
    :=\
    -0.43
     hâ
    -0.43
    </s>
    -0.42
    POSITIVE LOGITS
     Absatz
    0.70
     subsection
    0.66
     subsections
    0.66
    $_['
    0.65
     paragraphs
    0.62
     paragraph
    0.61
    ⒝
    0.60
    ModelAdmin
    0.59
     Subsection
    0.59
     paragraphe
    0.58
    Activations Density 0.526%

    No Known Activations