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. 30833
    Prev
    Next
    INDEX
    Explanations

    code elements related to React component structure

    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
    saga
    -0.80
    "]];
    -0.57
    _));
    -0.54
     PUBLICATIONS
    -0.51
    +#+#
    -0.50
     zast
    -0.50
    ]--;
    -0.49
    "]}
    -0.48
    }];
    -0.47
    دانشنامهٔ
    -0.47
    POSITIVE LOGITS
    Container
    0.66
     Container
    0.60
     container
    0.51
    principalTable
    0.51
     getItemCount
    0.49
    container
    0.49
    AnchorStyles
    0.48
     merkezi
    0.47
    CloseOperation
    0.44
    CONTAINER
    0.43
    Activations Density 0.000%

    No Known Activations