© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 1855
    Prev
    Next
    INDEX
    Explanations

    sentences that contain important contextual phrases or references about a situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Efq
    -0.87
     للمعارف
    -0.78
    MemoryWarning
    -0.70
     ―――――
    -0.69
    ratulations
    -0.65
    hicle
    -0.65
     iſt
    -0.65
     */;
    -0.64
    ^(@)
    -0.64
    chufe
    -0.63
    POSITIVE LOGITS
     propOrder
    0.56
    UnknownFieldSet
    0.53
    ↵↵
    0.53
    didSet
    0.50
    cuadro
    0.49
     ostavi
    0.47
    <eos>
    0.46
     Kennt
    0.46
    findpost
    0.45
     .
    0.44
    Activations Density 1.345%

    No Known Activations