© 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. 4-GEMMASCOPE-RES-16K
    6. 3316
    Prev
    Next
    INDEX
    Explanations

    repeated phrases or common structures in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]-->
    -0.64
    原始内容存档于
    -0.57
    ########.
    -0.56
    hearsal
    -0.53
    /***/
    -0.52
     phép
    -0.52
    '];?>
    -0.50
     Barnet
    -0.50
     einzu
    -0.50
    savevideo
    -0.50
    POSITIVE LOGITS
     on
    1.16
     On
    1.15
    On
    1.09
    onthe
    1.00
     ON
    1.00
    OnThe
    0.93
     на
    0.83
     وعلى
    0.81
    isOn
    0.80
     trên
    0.78
    Activations Density 0.201%

    No Known Activations