© 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. 40-GEMMASCOPE-RES-16K
    6. 6053
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific roles and responsibilities in programming or job descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     “
    -0.48
    ніципалі
    -0.44
    rungsseite
    -0.36
     pihaknya
    -0.34
    :✨
    -0.33
     autorytatywna
    -0.32
    abestanden
    -0.29
    RepeatedField
    -0.29
    </sub>
    -0.29
    cookieParser
    -0.28
    POSITIVE LOGITS
    ."
    2.38
    ".
    2.23
    ",
    2.23
    "
    
    2.20
    ?"
    2.19
    !"
    2.19
    ,"
    2.09
    .",
    2.08
    )"
    2.08
    ";
    2.08
    Activations Density 5.408%

    No Known Activations