© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 5695
    Prev
    Next
    INDEX
    Explanations

    expressions relating to statistical analysis or modeling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     كومونز
    -1.20
    VERTISEMENT
    -1.16
    leſs
    -1.03
    NUMX
    -1.03
    Lycka
    -1.03
    CHREIB
    -1.00
     CommandType
    -0.98
     BorderRadius
    -0.96
     RSITY
    -0.96
    ſhip
    -0.95
    POSITIVE LOGITS
    ↵
    2.78
    ↵↵
    2.11
    ↵↵↵
    1.87
    <eos>
    1.85
    ↵↵↵↵
    1.63
    ↵↵↵↵↵
    1.51
    ↵↵↵↵↵↵
    1.36
    ↵↵↵↵↵↵↵
    1.33
    <h2>
    1.30
    ↵↵↵↵↵↵↵↵↵
    1.25
    Activations Density 1.852%

    No Known Activations