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-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 8573
    Prev
    Next
    INDEX
    Explanations

    scientific terminology related to gene regulation and molecular biology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     виправивши
    -0.67
    RepeatedField
    -0.63
    tagHelperRunner
    -0.59
    ContentLoaded
    -0.57
    DrawerToggle
    -0.55
    borderSide
    -0.54
     beſte
    -0.54
    jsxFileName
    -0.54
    ToScroll
    -0.54
     snippetHide
    -0.53
    POSITIVE LOGITS
    IntentFilter
    0.43
     μεγ
    0.38
     eğitim
    0.35
     potrzeby
    0.34
     zanah
    0.33
     στιγ
    0.33
     akşam
    0.33
     Weitere
    0.33
    ánto
    0.32
     związ
    0.32
    Activations Density 3.672%

    No Known Activations