© 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. 16-GEMMASCOPE-RES-16K
    6. 3527
    Prev
    Next
    INDEX
    Explanations

    HTML tags, attributes, and their associated values

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

    HTML or code content

    np_acts-logits-general · gemini-2.0-flash

    character encoding metadata

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     إليها
    -0.43
    ny
    -0.43
    neth
    -0.42
     maken
    -0.42
     بلد
    -0.40
     another
    -0.40
    Хьажоргаш
    -0.40
    ान्त
    -0.40
     ]);
    -0.39
    কার
    -0.39
    POSITIVE LOGITS
     autorytatywna
    1.05
     ModelExpression
    0.93
    styleType
    0.88
    Autoritní
    0.88
     resourceCulture
    0.86
     CiNii
    0.85
    下载附件
    0.82
    makeConstraints
    0.82
    Hentet
    0.78
    RenderAtEndOf
    0.78
    Activations Density 0.203%

    No Known Activations