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. 7-GEMMASCOPE-RES-16K
    6. 11685
    Prev
    Next
    INDEX
    Explanations

    metrics and statistics related to sports performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onom
    -0.62
     تضيفلها
    -0.42
    uscular
    -0.42
    cain
    -0.41
     térmica
    -0.41
     dipl
    -0.41
    時候
    -0.40
     kár
    -0.40
    fton
    -0.40
    eri
    -0.40
    POSITIVE LOGITS
    новништво
    0.80
     AssemblyTitle
    0.76
    tvguidetime
    0.73
    complexType
    0.67
     gynhyrchwyd
    0.65
     BrowserModule
    0.65
     bezeichneter
    0.64
    RTGC
    0.63
    脚注の使い方
    0.63
    styleUrls
    0.63
    Activations Density 0.125%

    No Known Activations