© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 86018
    Prev
    Next
    INDEX
    Explanations

    indicators of successful outcomes or positive trends

    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
    Билгалдахарш
    -0.61
     otomatig
    -0.60
     Administrativna
    -0.56
    sidemargin
    -0.51
    Autoritní
    -0.50
    "}")
    -0.49
    TagMode
    -0.47
     ComVisible
    -0.47
    +#+#
    -0.46
    сылкі
    -0.46
    POSITIVE LOGITS
     praising
    0.49
    Praise
    0.47
    praise
    0.46
     Praise
    0.45
     praise
    0.45
     praised
    0.45
    Positive
    0.44
    proud
    0.41
     обна
    0.40
     praises
    0.39
    Activations Density 0.043%

    No Known Activations