© 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. 11780
    Prev
    Next
    INDEX
    Explanations

    names and attributes, particularly in the context of individuals and organizations

    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
     Fe
    -0.61
     fe
    -0.58
    的感覺
    -0.52
    setopt
    -0.51
    ancio
    -0.51
    ᾷ
    -0.50
    waitUntil
    -0.50
     beira
    -0.50
    GenerationType
    -0.50
    的看着
    -0.49
    POSITIVE LOGITS
    DebuggerNonUser
    0.87
    ValueStyle
    0.78
     itſelf
    0.70
    ό
    0.68
    TypedDataSet
    0.68
     Sciento
    0.66
    netbeans
    0.64
     незавершена
    0.63
    LEncoder
    0.62
     Dormit
    0.62
    Activations Density 0.283%

    No Known Activations