Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 6238
    Prev
    Next
    INDEX
    Explanations

    references and citations in academic or scientific texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ագրություններ
    -0.74
     autorytatywna
    -0.69
    Datuak
    -0.68
    MigrationBuilder
    -0.66
     للمعارف
    -0.65
     semelh
    -0.63
    extAlignment
    -0.60
    +#+#
    -0.60
     Walkover
    -0.60
    RotationOrder
    -0.59
    POSITIVE LOGITS
     resourceCulture
    0.70
    Przypisy
    0.42
    Einzelnachweise
    0.40
    MergeFrom
    0.35
    Vegeu
    0.35
    Erreferentziak
    0.33
    Източници
    0.33
     An
    0.30
     disponibilités
    0.30
    MockBean
    0.29
    Activations Density 1.259%

    No Known Activations