© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 119743
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     Mow
    -0.46
    IntoConstraints
    -0.41
     penas
    -0.41
    eably
    -0.40
    MLLoader
    -0.39
    inquirer
    -0.38
    Middle
    -0.38
     Middle
    -0.37
     middle
    -0.37
     Rücks
    -0.37
    POSITIVE LOGITS
    fjspx
    2.34
    $__
    1.12
    ($__
    0.66
    OGND
    0.59
    enderror
    0.56
     يتيمه
    0.56
    tagPool
    0.55
    oa̍t
    0.51
    Personensuche
    0.49
     AssemblyCompany
    0.48
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.