© 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. 10-GEMMASCOPE-RES-16K
    11. 12477
    Prev
    Next
    INDEX
    Explanations

    symbols and formatting indicators commonly used in programming and technical documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    %"),
    -0.57
    >--}}
    -0.55
    atience
    -0.52
     <>",
    -0.51
    ')";
    -0.51
    ]),
    -0.51
    >-->
    -0.50
    )"),
    -0.50
     "..\..\..\
    -0.49
    thâu
    -0.49
    POSITIVE LOGITS
    RenderAtEndOf
    0.74
    存于互联网档案馆
    0.71
    LLocation
    0.68
     ProtoMessage
    0.68
    GraphicsUnit
    0.66
    tvguidetime
    0.65
     MainAxisSize
    0.65
     NSCoder
    0.63
     getItemId
    0.62
    endphp
    0.61
    Activations Density 0.844%

    No Known Activations