© 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. 10113
    Prev
    Next
    INDEX
    Explanations

    references to struggles and adaptations in personal challenges

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

    doing things alone

    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
     favourably
    -0.64
     kaynağından
    -0.60
     favorably
    -0.59
     initComponents
    -0.55
     Easily
    -0.52
    principalTable
    -0.52
     utafitiHapana
    -0.52
     Properly
    -0.50
    Aprove
    -0.50
     صوتيه
    -0.49
    POSITIVE LOGITS
     uncertain
    0.83
     unfamiliar
    0.79
     unsure
    0.71
     hastily
    0.70
     uncertainty
    0.68
     ungew
    0.65
     incertidumbre
    0.63
     reluctantly
    0.62
     makeshift
    0.62
     terpaksa
    0.61
    Activations Density 0.071%

    No Known Activations