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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 51783
    Prev
    Next
    INDEX
    Explanations

    actions related to opening or revealing something, particularly packages, containers, or gifts.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @dribnet

    references to the act of opening or unpacking items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     bună
    -0.47
     Bewußt
    -0.43
     Lijst
    -0.41
     européennes
    -0.41
     förb
    -0.41
    DataAnnotations
    -0.41
     nadzieję
    -0.40
     Fähigkeiten
    -0.39
     duração
    -0.39
     valsty
    -0.39
    POSITIVE LOGITS
     unpack
    0.65
     unpacking
    0.64
    unpack
    0.55
    opened
    0.52
    GTCX
    0.51
    RTEX
    0.50
    opening
    0.50
    CardContent
    0.49
     unpacked
    0.48
     unopened
    0.46
    Activations Density 0.011%

    No Known Activations