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. 20-GEMMASCOPE-RES-131K
    6. 95064
    Prev
    Next
    INDEX
    Explanations

    high-frequency or prominently mentioned words and phrases in the text

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

    references

    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
     للاسماء
    -0.90
     Италијани
    -0.86
     Савезне
    -0.84
    Derbyniad
    -0.82
    +#+#
    -0.81
    ⟬
    -0.80
    :✨
    -0.80
    tvguidetime
    -0.79
    <pad>
    -0.79
    [@BOS@]
    -0.77
    POSITIVE LOGITS
    1
    0.29
    8
    0.27
     
    0.26
    2
    0.26
    </b>
    0.26
    9
    0.25
    3
    0.25
    6
    0.25
    ;
    0.24
     among
    0.23
    Activations Density 0.036%

    No Known Activations