© 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. 3-GEMMASCOPE-RES-16K
    6. 8665
    Prev
    Next
    INDEX
    Explanations

    instances of an underscore character as a placeholder

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     invokingState
    -0.92
     Paglinawan
    -0.89
     Roskov
    -0.87
     Surname
    -0.86
     itſelf
    -0.85
     myſelf
    -0.82
     ligiloj
    -0.81
     estimés
    -0.78
     <>",
    -0.76
     Hift
    -0.75
    POSITIVE LOGITS
     and
    0.69
    ↵
    0.67
    </strong>
    0.59
    ,
    0.57
    <eos>
    0.55
     S
    0.55
     (
    0.55
     T
    0.51
    );
    0.49
    ),
    0.49
    Activations Density 0.068%

    No Known Activations