© 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. 5109
    Prev
    Next
    INDEX
    Explanations

    references to financial investments

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

    investments and expenditures

    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
     impossible
    -0.53
    buttonStyle
    -0.50
     opinião
    -0.48
    impossible
    -0.47
     Cullen
    -0.47
     opinion
    -0.46
    ophenyl
    -0.46
    owner
    -0.46
    opinion
    -0.46
    httphttps
    -0.45
    POSITIVE LOGITS
     investments
    1.38
    Investments
    1.20
     Investments
    1.17
     inversiones
    0.78
     investimentos
    0.70
    invest
    0.67
     investissements
    0.58
     expenditures
    0.56
     INVEST
    0.55
     innovations
    0.55
    Activations Density 0.007%

    No Known Activations