© 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. 7-GEMMASCOPE-RES-16K
    6. 1909
    Prev
    Next
    INDEX
    Explanations

    concepts related to modeling and representation in various scientific frameworks

    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
     bénéfice
    -0.56
     <<<<<<<<<<<<<<
    -0.55
    MIDDLEWARE
    -0.54
    JoinColumn
    -0.53
    EventLoop
    -0.52
    emptory
    -0.51
     historischen
    -0.51
    IBarButtonItem
    -0.51
    __":
    
    -0.50
    SPJ
    -0.50
    POSITIVE LOGITS
     describing
    0.80
     REPRESENT
    0.75
    rungsseite
    0.74
     representation
    0.74
     décrire
    0.74
     Representing
    0.70
     captures
    0.69
     capturing
    0.69
     describe
    0.68
     represented
    0.67
    Activations Density 0.710%

    No Known Activations