Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 9563
    Prev
    Next
    INDEX
    Explanations

    family relationships and lineage information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    قص
    -0.55
    endcsname
    -0.52
    Abp
    -0.51
     =>
    
    -0.51
     خلق
    -0.51
    __*/
    -0.48
     européennes
    -0.47
     répondu
    -0.46
    Xiv
    -0.46
     naturelles
    -0.45
    POSITIVE LOGITS
    encodeWith
    0.69
    RenderAtEndOf
    0.66
    contentLoaded
    0.63
    WithIOException
    0.62
    protoimpl
    0.60
    Personendaten
    0.59
    สบ
    0.57
    ofday
    0.56
    OGND
    0.56
    DeleteBehavior
    0.55
    Activations Density 0.036%

    No Known Activations