Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 8035
    Prev
    Next
    INDEX
    Explanations

    words related to technology and devices, particularly with a focus on functionality and control

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    혔
    -0.46
     string
    -0.46
    savevideo
    -0.44
    }/${
    -0.43
    uffle
    -0.43
    Edited
    -0.43
    Далее
    -0.42
    iska
    -0.42
    alit
    -0.42
     Projekt
    -0.42
    POSITIVE LOGITS
     gynhyrchwyd
    0.67
     kaarangay
    0.65
    KommentareTeilen
    0.63
     esternos
    0.62
     thither
    0.62
    protoimpl
    0.60
    Билгалдахарш
    0.60
     ujednoznacz
    0.58
    ImageContext
    0.57
     Workmen
    0.56
    Activations Density 0.486%

    No Known Activations