© 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. 12723
    Prev
    Next
    INDEX
    Explanations

    technical specifications and development updates related to software and clinical studies

    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
     StatelessWidget
    -0.42
    újo
    -0.35
    ngdoc
    -0.34
     veau
    -0.33
     怎样
    -0.33
    AutoScaleMode
    -0.32
    guiente
    -0.32
     odpor
    -0.32
    +#+#
    -0.32
    ertale
    -0.31
    POSITIVE LOGITS
     ongoing
    1.49
     underway
    1.46
    正在
    1.40
     pending
    1.37
     undergoing
    1.30
     đang
    1.30
     sedang
    1.29
    ongoing
    1.28
     Ongoing
    1.26
     unfinished
    1.23
    Activations Density 0.801%

    No Known Activations