© 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. 8-GEMMASCOPE-RES-16K
    6. 8947
    Prev
    Next
    INDEX
    Explanations

    references to missing items or people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/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.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bezeichneter
    -0.62
    <bos>
    -0.58
    atguigu
    -0.57
    Personendaten
    -0.56
    ReusableCell
    -0.56
     بيها
    -0.55
    __*/
    -0.54
     precedence
    -0.54
    astia
    -0.53
     infine
    -0.52
    POSITIVE LOGITS
     whereabouts
    0.78
    ConstraintMaker
    0.71
     lost
    0.71
     somewhere
    0.61
     Somewhere
    0.59
    不見
    0.59
    不见
    0.56
     Lost
    0.56
    tras
    0.53
    Lost
    0.53
    Activations Density 0.296%

    No Known Activations