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. 9-GEMMASCOPE-RES-16K
    6. 9321
    Prev
    Next
    INDEX
    Explanations

    terms related to regulation and management in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/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.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     or
    -0.69
     and
    -0.60
    ])));
    -0.56
    Einzelnachweise
    -0.49
    ***********/
    -0.49
     
    -0.47
    NamedQueries
    -0.46
    <eos>
    -0.45
    ************/
    -0.45
     (
    -0.44
    POSITIVE LOGITS
    følgelig
    0.74
     BoxFit
    0.74
    EDEFAULT
    0.74
    PyExc
    0.69
    }{*}{
    0.68
     оригіналу
    0.67
    parsedMessage
    0.65
     مشين
    0.65
    uxxxx
    0.64
     onCancelled
    0.63
    Activations Density 0.545%

    No Known Activations