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. 35708
    Prev
    Next
    INDEX
    Explanations

    academic research projects and methodologies

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

    investigate, showed, demonstrate, determine, measure

    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
     SwitchCompat
    -0.45
    Sklici
    -0.43
     católica
    -0.39
     déput
    -0.38
     chiunque
    -0.38
     religieuse
    -0.37
     chrétien
    -0.37
    ContextCompat
    -0.37
     busy
    -0.35
     uten
    -0.35
    POSITIVE LOGITS
    ագրություններ
    0.61
     CreateTagHelper
    0.51
    parsedMessage
    0.50
    帖最后由
    0.48
    +:+
    0.48
    addPreferredGap
    0.47
    RegressionTest
    0.46
    مقاله
    0.45
     ILogger
    0.45
    +#+#
    0.44
    Activations Density 0.011%

    No Known Activations