Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 4922
    Prev
    Next
    INDEX
    Explanations

    parentheses and slashes, likely indicating formatting or code syntax elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    }>;
    -0.89
     ModelExpression
    -0.80
    LLocation
    -0.79
    ]")]
    -0.76
     Audiodateien
    -0.75
     <=",
    -0.75
     getItemId
    -0.74
    })));
    -0.74
     CGSize
    -0.74
    brainly
    -0.72
    POSITIVE LOGITS
    DebuggerStep
    0.55
     jacks
    0.49
    Contrato
    0.48
     of
    0.47
    牒
    0.47
    Unmount
    0.47
    siv
    0.47
    Derivative
    0.46
    pede
    0.45
     cap
    0.44
    Activations Density 0.024%

    No Known Activations