© 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. 9-GEMMASCOPE-RES-131K
    6. 99103
    Prev
    Next
    INDEX
    Explanations

    specific identifiers and categorizations related to data or objects, including positive and negative labels along with specific notation symbols in mathematical or scientific contexts

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

    New German Jazz

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     resourceCulture
    -0.43
    CloseOperation
    -0.42
    #+#
    -0.40
     FontWeight
    -0.39
    WaitGroup
    -0.39
    XmlAccessType
    -0.37
    NOPQRST
    -0.35
     hoạch
    -0.34
     createState
    -0.34
    Personendaten
    -0.34
    POSITIVE LOGITS
    TypedDataSet
    0.63
    tagHelperRunner
    0.55
    ########.
    0.49
     autorytatywna
    0.49
     kasarigan
    0.46
     nakalista
    0.46
    hyrchwyd
    0.43
    $_['
    0.43
    jsxFileName
    0.43
    icordia
    0.42
    Activations Density 0.610%

    No Known Activations