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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 2179
    Prev
    Next
    INDEX
    Explanations

    initiation patterns in written text

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

    Code, questions, or articles

    np_acts-logits-general · gemini-2.0-flash

    def, Buy, Sub, Health, Preliminary, Blog

    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
     lenker
    -0.71
     ***!
    -0.67
    tagHelperRunner
    -0.62
    Jeografia
    -0.56
     &___
    -0.56
    *}
    -0.55
    twimg
    -0.53
     مشين
    -0.52
     ''}
    -0.51
    Rujuakan
    -0.51
    POSITIVE LOGITS
     child
    0.67
    child
    0.64
     jScrollPane
    0.60
    ),
    0.59
     center
    0.58
    backgroundColor
    0.57
    )).
    0.56
     ),
    0.55
     backgroundColor
    0.55
    )),
    0.54
    Activations Density 0.008%

    No Known Activations