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-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 6851
    Prev
    Next
    INDEX
    Explanations

    aspects related to research methodology and data evaluation in studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.56
    newswire
    -0.54
     pourtant
    -0.50
    enschaft
    -0.48
    thenReturn
    -0.46
    migrationBuilder
    -0.45
    almost
    -0.43
    itié
    -0.43
    ếng
    -0.42
     cubiertas
    -0.40
    POSITIVE LOGITS
     any
    1.64
     eventuali
    1.34
     Any
    1.31
    Any
    1.29
     quaisquer
    1.17
     anything
    1.15
    any
    1.10
    anything
    1.01
     Anything
    0.99
    任何
    0.99
    Activations Density 0.545%

    No Known Activations