© 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. 18-GEMMASCOPE-RES-16K
    11. 3978
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to legal proceedings and disclosures

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

    preceding "said" or comment-related words

    np_acts-logits-general · gemini-2.0-flash

    not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AccessException
    -0.48
     DO
    -0.46
     rarely
    -0.43
     only
    -0.42
    Only
    -0.42
    almost
    -0.42
     hardly
    -0.41
     Chance
    -0.40
    akei
    -0.40
    Permalink
    -0.40
    POSITIVE LOGITS
     specifics
    0.98
     exact
    0.92
     precise
    0.82
     details
    0.82
    具体
    0.82
    exact
    0.82
    pecific
    0.81
     exacte
    0.80
     officially
    0.79
     precisely
    0.78
    Activations Density 0.375%

    No Known Activations