© 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. 4-GEMMASCOPE-RES-16K
    6. 2420
    Prev
    Next
    INDEX
    Explanations

    references to people with notable accomplishments or roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OGND
    -0.67
     useParams
    -0.46
     cytok
    -0.46
    kembangan
    -0.45
    SPATH
    -0.44
    olstadt
    -0.44
     ruler
    -0.42
    r
    -0.42
    thalle
    -0.42
     αγ
    -0.42
    POSITIVE LOGITS
     board
    0.74
     boards
    0.72
    board
    0.71
     createState
    0.68
    </caption>
    0.68
    Boards
    0.65
    ∉
    0.65
    ……"
    0.65
     Boards
    0.64
     jurors
    0.63
    Activations Density 0.445%

    No Known Activations