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. 21754
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to pivoting or rotational movements

    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
     La
    -0.40
    Distribuzione
    -0.39
     Es
    -0.38
    setLoading
    -0.38
    Class
    -0.37
     &
    -0.36
    La
    -0.36
    Ha
    -0.36
    Law
    -0.36
    as
    -0.36
    POSITIVE LOGITS
     Pivot
    1.15
    pivot
    1.12
     pivot
    1.10
    Pivot
    1.07
     Piv
    0.84
     piv
    0.84
     pivo
    0.79
     pivotal
    0.78
    piv
    0.76
     Pardavimas
    0.70
    Activations Density 0.006%

    No Known Activations