© 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. 20-GEMMASCOPE-RES-16K
    6. 11366
    Prev
    Next
    INDEX
    Explanations

    expressions indicating capability or potential

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     the
    -0.43
    hésite
    -0.42
     and
    -0.40
     is
    -0.40
     these
    -0.40
     knji
    -0.38
     merkez
    -0.36
     graduación
    -0.36
     darb
    -0.36
     it
    -0.36
    POSITIVE LOGITS
    Able
    0.86
     Able
    0.81
     смог
    0.78
    unable
    0.73
    urlopen
    0.72
     able
    0.72
    TargetException
    0.71
    extAlignment
    0.71
    EndInit
    0.71
    oer
    0.70
    Activations Density 0.077%

    No Known Activations