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. 20-GEMMASCOPE-RES-16K
    6. 48
    Prev
    Next
    INDEX
    Explanations

    references to being "behind" something, particularly in contexts implying secrecy or concealment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.47
    CppMethod
    -0.47
     dinámico
    -0.46
    road
    -0.46
    Tikang
    -0.45
    PYX
    -0.45
    فیلم
    -0.44
     Road
    -0.43
    iastes
    -0.42
     Roads
    -0.42
    POSITIVE LOGITS
     scenes
    1.36
     Behind
    1.29
    Behind
    1.26
     behind
    1.25
    behind
    1.18
     BEHIND
    1.17
    scenes
    1.15
     Scenes
    1.05
     closed
    1.03
    Scenes
    1.03
    Activations Density 0.062%

    No Known Activations