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. 39-GEMMASCOPE-RES-16K
    6. 4286
    Prev
    Next
    INDEX
    Explanations

    specific chemical compounds and their concentrations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ſelf
    -0.54
     pleaſure
    -0.48
     Majefty
    -0.48
     actionMode
    -0.46
     myſelf
    -0.44
     purpoſe
    -0.43
     ſte
    -0.42
    actionMode
    -0.42
    ſelves
    -0.42
     juſ
    -0.41
    POSITIVE LOGITS
     IS
    0.57
    ZO
    0.57
     IO
    0.55
     l
    0.54
    IO
    0.52
    IS
    0.52
    SO
    0.51
    lO
    0.50
     IG
    0.50
    l
    0.50
    Activations Density 1.963%

    No Known Activations