© 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. 9-GEMMASCOPE-RES-131K
    6. 31178
    Prev
    Next
    INDEX
    Explanations

    references to various types of sausage and related meat products

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

    sausage, salami, and related meats

    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
    posedge
    -0.68
     كومونز
    -0.59
    vább
    -0.55
     חיצוניים
    -0.53
    iterranée
    -0.51
    <%=
    -0.50
    ℬ
    -0.50
    cassert
    -0.49
    泊
    -0.48
     ligiloj
    -0.47
    POSITIVE LOGITS
     sausage
    2.22
     Sausage
    2.02
     sausages
    1.77
     sosis
    0.99
    saus
    0.91
    wurst
    0.77
     chorizo
    0.75
     meat
    0.75
     MEAT
    0.73
    SequentialGroup
    0.68
    Activations Density 0.002%

    No Known Activations