© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 7086
    Prev
    Next
    INDEX
    Explanations

    punctuation and various symbols within the text

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

    Punctuation: Quotation marks and commas

    np_acts-logits-general · gemini-2.0-flash

    closing quotation marks

    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
    expandindo
    -0.62
    ).\\
    -0.58
    ?】
    -0.53
    FTFY
    -0.51
     estimés
    -0.50
    .)}
    -0.50
    pshire
    -0.50
    ;\\
    -0.50
    LinkId
    -0.50
    。】
    -0.48
    POSITIVE LOGITS
    ”
    1.15
    」
    1.13
    ""
    0.99
    ’’
    0.99
    ''
    0.96
    ″
    0.93
     ”
    0.92
    »
    0.89
    rdquo
    0.85
    "
    0.84
    Activations Density 0.149%

    No Known Activations