© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 1742
    Prev
    Next
    INDEX
    Explanations

    terms related to status effects and their attributes in gaming contexts

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

    numeric values and digits in code and technical text.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    gypte
    -0.40
    triangleq
    -0.39
    errmsg
    -0.38
    httphttps
    -0.38
    TagHelpers
    -0.38
    principalTable
    -0.37
     Advanced
    -0.37
     enx
    -0.37
    orsz
    -0.36
     Babe
    -0.36
    POSITIVE LOGITS
     resistance
    0.60
     resistances
    0.55
     regeneration
    0.54
     health
    0.54
     resistência
    0.53
     saúde
    0.50
     gynhyrchwyd
    0.49
     résistance
    0.49
     increases
    0.48
     resistencia
    0.48
    Activations Density 0.114%

    No Known Activations