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. 8-GEMMASCOPE-RES-16K
    6. 8483
    Prev
    Next
    INDEX
    Explanations

    results or implications in a theoretical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    providedIn
    -0.73
    sqcup
    -0.69
     hữu
    -0.61
    awtextra
    -0.61
    jsxFileName
    -0.61
    bigsqcup
    -0.59
    HasColumnType
    -0.58
    łgorzata
    -0.57
    andaag
    -0.53
    achim
    -0.51
    POSITIVE LOGITS
     Consequences
    1.12
     consequence
    1.11
     consequences
    1.10
    Consequences
    1.09
     Konsequ
    1.05
     implications
    1.01
     conséquence
    0.99
     implication
    0.97
     conséquences
    0.95
     inferences
    0.93
    Activations Density 0.477%

    No Known Activations