© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13848
    Prev
    Next
    INDEX
    Explanations

    elements related to data presentation or formatting in tables

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

    Table formatting or structure

    np_acts-logits-general · gemini-2.0-flash

    |

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    principalColumn
    -0.69
    parsedMessage
    -0.61
    dAtA
    -0.60
    awaiter
    -0.57
     endwhile
    -0.56
    MessageTagHelper
    -0.54
    MENAFN
    -0.54
     становника
    -0.54
    sizeCache
    -0.54
    msgTypes
    -0.54
    POSITIVE LOGITS
    colhead
    0.62
    hline
    0.62
    rzost
    0.44
    /**
    0.40
    <th>
    0.40
    Zeneca
    0.37
    poons
    0.37
     termes
    0.36
    TextBoxColumn
    0.36
     chrom
    0.35
    Activations Density 0.098%

    No Known Activations