© 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-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 13074
    Prev
    Next
    INDEX
    Explanations

    references to locations or geographical entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    city, state or country

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CURIAM
    -0.59
     esternos
    -0.58
    gucig
    -0.54
     cherchés
    -0.54
    antaranya
    -0.51
     aapt
    -0.51
    écrire
    -0.49
     TAMBÉM
    -0.49
     dibujado
    -0.49
    rungsseite
    -0.49
    POSITIVE LOGITS
    AddTagHelper
    0.41
     Alina
    0.41
     USA
    0.41
    ‭
    0.41
     Rei
    0.41
    Â
    0.40
     NY
    0.40
     р
    0.39
    ContextCompat
    0.39
     \
    0.39
    Activations Density 0.045%

    No Known Activations