© 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. 12802
    Prev
    Next
    INDEX
    Explanations

    words related to documentation and organization

    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
     Савезне
    -0.49
    onViewCreated
    -0.48
    RectangleBorder
    -0.46
     <<<<<<<<<<<<<<
    -0.45
    :✨
    -0.45
     AspNetCore
    -0.45
     NSCoder
    -0.44
     BoxDecoration
    -0.43
    @[+][
    -0.43
    ELTS
    -0.42
    POSITIVE LOGITS
    ary
    1.55
    ARY
    1.35
    aries
    1.26
     ary
    1.13
    ery
    1.11
    ory
    0.99
    airy
    0.97
    lary
    0.96
    arily
    0.91
    ERY
    0.89
    Activations Density 0.521%

    No Known Activations