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. 18-GEMMASCOPE-RES-16K
    6. 10102
    Prev
    Next
    INDEX
    Explanations

    technical terms related to physical dimensions and measurement units

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WEBPACK
    -0.52
     prank
    -0.52
     joke
    -0.52
     ostavi
    -0.52
    IsMutable
    -0.49
     متعلقه
    -0.49
     Joke
    -0.48
     jokes
    -0.47
     pranks
    -0.47
    Markov
    -0.47
    POSITIVE LOGITS
     units
    1.77
     unit
    1.64
     Units
    1.60
    Units
    1.53
    units
    1.52
     UNITS
    1.47
    Unit
    1.39
     Unit
    1.38
    unit
    1.34
    UNITS
    1.33
    Activations Density 0.275%

    No Known Activations