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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 25-GEMMASCOPE-RES-16K
    6. 3722
    Prev
    Next
    INDEX
    Explanations

    elements related to game development and configuration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    verständlich
    -0.54
    \%
    -0.49
    Referencer
    -0.48
    .:
    -0.48
    UnifiedTopology
    -0.48
    layın
    -0.47
    .}
    -0.47
     ciasc
    -0.46
     tanggung
    -0.46
    ."
    -0.46
    POSITIVE LOGITS
    exception
    0.79
    enums
    0.75
    exceptions
    0.73
    util
    0.66
     constants
    0.65
    constants
    0.63
    constant
    0.62
    dto
    0.62
    utils
    0.62
     exceptions
    0.61
    Activations Density 0.127%

    No Known Activations