Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 59144
    Prev
    Next
    INDEX
    Explanations

    specific syntax or structure in code-like text

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

    special characters and non-English words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Es
    -0.40
    cit
    -0.38
     Syl
    -0.38
    Syl
    -0.37
    cle
    -0.36
     Fores
    -0.36
     Jaz
    -0.36
     Hal
    -0.35
    dex
    -0.35
    Zap
    -0.35
    POSITIVE LOGITS
    adaptiveStyles
    0.70
     faſt
    0.68
     nakalista
    0.66
     anún
    0.63
    ſelves
    0.63
     snippetHide
    0.62
    లాలు
    0.62
     ſche
    0.59
     increí
    0.58
    __':
    
    0.57
    Activations Density 0.085%

    No Known Activations