© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 42520
    Prev
    Next
    INDEX
    Explanations

    concepts related to investment potential and risk management

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

    upside potential

    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
     BoxDecoration
    -0.43
     straat
    -0.40
    nodoc
    -0.40
    tazione
    -0.40
     mối
    -0.40
     bü
    -0.39
     tecniche
    -0.39
    UAGE
    -0.38
     voet
    -0.38
    GeneratedMessage
    -0.38
    POSITIVE LOGITS
     upside
    1.26
     downside
    1.00
     Upside
    0.92
     potential
    0.85
    potential
    0.77
     potencial
    0.75
    AddTagHelper
    0.70
     potentiel
    0.69
    Potential
    0.68
     POTENTIAL
    0.67
    Activations Density 0.047%

    No Known Activations