© 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. 14341
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to scientific measurements and statistical values

    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
    Fifty
    -0.74
    Forty
    -0.73
    Sixty
    -0.72
     Fifty
    -0.70
     Sixty
    -0.69
    三百
    -0.68
    hundreds
    -0.65
     Forty
    -0.65
     Seventy
    -0.64
     hundreds
    -0.63
    POSITIVE LOGITS
     eight
    1.44
     nine
    1.43
     seven
    1.39
     ten
    1.32
     eleven
    1.28
     six
    1.18
     twelve
    1.13
    eight
    1.10
     nueve
    1.09
     thirteen
    1.05
    Activations Density 2.674%

    No Known Activations