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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 10-GEMMASCOPE-RES-16K
    6. 10806
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific mechanisms and adverse effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     noqa
    -0.66
    참고
    -0.65
    ніципа
    -0.65
     InputDecoration
    -0.65
     LoggerFactory
    -0.65
    RTDA
    -0.64
    @[+][
    -0.64
    AxisAlignment
    -0.63
    CloseOperation
    -0.62
     TestBed
    -0.61
    POSITIVE LOGITS
    LookAnd
    0.59
     surla
    0.48
    XtraGrid
    0.46
     חיצוניים
    0.45
     MotionEvent
    0.44
     wireType
    0.43
    ,
    0.43
     so
    0.40
     movement
    0.39
     The
    0.38
    Activations Density 3.670%

    No Known Activations