© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 79717
    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
    tembre
    -0.35
     darum
    -0.33
    ants
    -0.31
     inside
    -0.31
     until
    -0.30
     plumas
    -0.30
    ンの
    -0.30
     künf
    -0.30
    inside
    -0.30
     bên
    -0.30
    POSITIVE LOGITS
    VolleyError
    6.63
    volley
    1.09
    GOTREF
    0.87
    setVerticalGroup
    0.81
    AddTagHelper
    0.77
    bootstrapcdn
    0.76
    RegistryLite
    0.74
    StoryboardSegue
    0.74
    DatabaseError
    0.74
     Volley
    0.73
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.