© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 6775
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to supplementary actions or attributes, often indicating conjunctions or relationships

    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
    TagMode
    -0.49
     createSlice
    -0.49
    záll
    -0.45
    fhir
    -0.44
    haya
    -0.42
    currentColor
    -0.41
    currentTarget
    -0.41
    utama
    -0.41
    idro
    -0.40
    reise
    -0.40
    POSITIVE LOGITS
     complemented
    1.20
     supplemented
    1.15
     complimented
    1.13
     accompanied
    1.09
     topped
    0.94
     backed
    0.93
    accompanied
    0.92
     accompagné
    0.88
    companied
    0.86
     paired
    0.85
    Activations Density 0.290%

    No Known Activations