© 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. 3-GEMMASCOPE-RES-16K
    11. 8119
    Prev
    Next
    INDEX
    Explanations

    phrases indicating necessity or irrelevance, particularly in the context of actions or decisions

    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
    PhysRevLett
    -0.56
    ArgumentParser
    -0.54
    HostException
    -0.54
    piecze
    -0.51
     Autorizaciones
    -0.49
     samlet
    -0.47
    amitié
    -0.45
    StackNavigator
    -0.45
    渍
    -0.45
     ever
    -0.44
    POSITIVE LOGITS
     irrelevant
    0.94
    XDECREF
    0.83
    QMetaType
    0.81
     Irrelevant
    0.80
    AutoScaleMode
    0.77
     neither
    0.76
     AssemblyCulture
    0.74
    keyColumn
    0.73
     unrelated
    0.72
    principalColumn
    0.72
    Activations Density 0.487%

    No Known Activations