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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 23-GEMMASCOPE-RES-16K
    6. 12038
    Prev
    Next
    INDEX
    Explanations

    sentences that begin with the word "One."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     تضيفلها
    -0.65
    stdafx
    -0.55
    scriptcase
    -0.53
    AndroidJUnit
    -0.52
     ModelExpression
    -0.50
    MigrationBuilder
    -0.50
    ldb
    -0.50
     respectively
    -0.49
    ంది
    -0.48
    :].
    -0.47
    POSITIVE LOGITS
     thing
    0.79
     cannot
    0.75
     wonders
    0.75
     could
    0.74
     important
    0.74
     might
    0.73
     must
    0.72
    cannot
    0.72
     voordeel
    0.72
     major
    0.71
    Activations Density 0.155%

    No Known Activations