© 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-2-9B
    4. Residual Stream - 16k
    5. 35-GEMMASCOPE-RES-16K
    6. 6809
    Prev
    Next
    INDEX
    Explanations

    references to issues and problems, especially in a context of problem-solving

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ӕ
    -0.43
     Савезне
    -0.40
     myśli
    -0.39
    featureID
    -0.37
     škoda
    -0.35
     Paglinawan
    -0.34
     mogelijkheden
    -0.34
    OGND
    -0.34
    Diweddarwch
    -0.34
     készült
    -0.33
    POSITIVE LOGITS
     solved
    0.99
     solving
    0.95
     Solved
    0.86
    solving
    0.84
     Solving
    0.83
     Problem
    0.79
    solved
    0.79
     solvers
    0.77
    Solving
    0.76
    olving
    0.76
    Activations Density 0.178%

    No Known Activations