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. 15-GEMMASCOPE-RES-16K
    6. 12914
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistics related to health or medical conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ruptedException
    -0.60
     Permanent
    -0.58
    RuleContext
    -0.56
     permanent
    -0.56
    ASSOC
    -0.55
    TypedDataSet
    -0.54
    permanent
    -0.53
    Naissance
    -0.53
    ็บ
    -0.52
    Gone
    -0.52
    POSITIVE LOGITS
     saving
    0.59
     autorytatywna
    0.57
     making
    0.57
     running
    0.57
     reflecting
    0.56
    saving
    0.56
     using
    0.55
     taking
    0.55
     tracking
    0.55
     being
    0.54
    Activations Density 0.528%

    No Known Activations