© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 1199
    Prev
    Next
    INDEX
    Explanations

    special character sequences and formatting elements used in markup or code

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

    code delimiters and abstract

    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
    Биография
    -0.39
    Carcinogenicity
    -0.36
     Nachteile
    -0.34
    Personendaten
    -0.34
    rhosis
    -0.32
    fjspx
    -0.32
     pioggia
    -0.31
    AnchorTagHelper
    -0.31
     ComVisible
    -0.31
    ngths
    -0.30
    POSITIVE LOGITS
    WriteTagHelper
    0.56
    #+#
    0.56
    RTDA
    0.54
    ValueStyle
    0.54
    odils
    0.52
     nakalista
    0.48
    acier
    0.46
    ispo
    0.46
    ValueGenerated
    0.45
     defaultstate
    0.45
    Activations Density 0.027%

    No Known Activations