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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 42388
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter 'e' in various contexts

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

    technical identifiers and data fragments

    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
     souhaitez
    -0.36
     Christiansen
    -0.36
     תק
    -0.34
     verrez
    -0.33
    iramente
    -0.32
     contigo
    -0.32
     اللا
    -0.32
     יוצ
    -0.32
     recevez
    -0.32
     iNdEx
    -0.31
    POSITIVE LOGITS
    tvguidetime
    0.72
     препратки
    0.66
     Meksiku
    0.63
    MessageOf
    0.59
    NameInMap
    0.59
    GEBURTSDATUM
    0.58
     hikariConfig
    0.55
     nakalista
    0.54
    RTGC
    0.54
    RTSC
    0.53
    Activations Density 0.001%

    No Known Activations