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. 24-GEMMASCOPE-RES-16K
    6. 13971
    Prev
    Next
    INDEX
    Explanations

    references to academic publications and their associated citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Appears before "Eds" or "Ed" in citations

    np_acts-logits-general · gemini-2.0-flash

    academic citations for editors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <?
    -0.75
    
    -0.69
    υμα
    -0.63
    dataclass
    -0.61
    imageshack
    -0.61
     ::=
    -0.60
    makeConstraints
    -0.60
     للمعارف
    -0.58
     @"
    -0.57
    "><?=
    -0.57
    POSITIVE LOGITS
    Ed
    1.11
     Ed
    1.05
     ed
    1.01
    Eds
    1.00
    ed
    0.99
     Eds
    0.95
    eds
    0.87
     Editor
    0.86
     editor
    0.84
     Editors
    0.84
    Activations Density 0.063%

    No Known Activations