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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 106057
    Prev
    Next
    INDEX
    Explanations

    references to memory technologies and their applications in nanoscale systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    )]);
    -0.40
     GenerationType
    -0.38
     bParam
    -0.37
    %)$
    -0.37
    WritableDatabase
    -0.37
    ThroughAttribute
    -0.36
    ']));
    -0.34
    )});
    -0.34
     aggreg
    -0.33
    czak
    -0.33
    POSITIVE LOGITS
    MessageTagHelper
    0.59
     '\\;'
    0.57
     ModelExpression
    0.56
    MeasureSpec
    0.48
    rugu
    0.47
    guisement
    0.46
     tartalomajánló
    0.45
     Giá
    0.45
    inSlope
    0.44
    tagHelperRunner
    0.44
    Activations Density 0.251%

    No Known Activations