© 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. 5-GEMMASCOPE-RES-16K
    6. 8457
    Prev
    Next
    INDEX
    Explanations

    references to various types of indices or indexing systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CFLAGS
    -0.77
     juſt
    -0.77
    SUNG
    -0.76
     getArguments
    -0.75
    ForRow
    -0.74
     $_"
    -0.74
    Искәрмәләр
    -0.73
     Crot
    -0.72
    utdown
    -0.71
    tshell
    -0.71
    POSITIVE LOGITS
     index
    2.19
     Index
    2.07
     INDEX
    2.04
    index
    1.95
    Index
    1.92
    INDEX
    1.89
     indexes
    1.80
     indices
    1.79
     getIndex
    1.69
     Indexes
    1.68
    Activations Density 0.126%

    No Known Activations