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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 203
    Prev
    Next
    INDEX
    Explanations

    attempted actions or efforts to achieve something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SharedCtor
    -0.57
     AssemblyCulture
    -0.48
    tonode
    -0.42
    principalTable
    -0.41
     Roost
    -0.40
    libatkan
    -0.40
     timeval
    -0.39
     faptul
    -0.37
     BorderRadius
    -0.36
    lidays
    -0.36
    POSITIVE LOGITS
    attempt
    0.85
     attempts
    0.84
    trying
    0.83
     attempt
    0.81
     trying
    0.81
    Attempt
    0.80
    Trying
    0.79
     versucht
    0.79
     attempted
    0.78
    Attempts
    0.78
    Activations Density 0.242%

    No Known Activations