© 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. 13159
    Prev
    Next
    INDEX
    Explanations

    phrases related to communication and online interactions

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

    locations and links

    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
     kasarigan
    -0.79
    KommentareTeilen
    -0.59
    styleType
    -0.57
    !*\
    -0.55
    esModule
    -0.55
    UnusedPrivate
    -0.54
     SqlCommand
    -0.53
     iNdEx
    -0.52
    sizeCache
    -0.52
    HttpFoundation
    -0.51
    POSITIVE LOGITS
     above
    0.47
     this
    0.47
    enlace
    0.42
     ABOVE
    0.42
     acá
    0.42
     here
    0.41
     montanha
    0.41
     ahí
    0.41
    vidéo
    0.41
     aquí
    0.40
    Activations Density 0.085%

    No Known Activations