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. 16-GEMMASCOPE-RES-16K
    6. 8302
    Prev
    Next
    INDEX
    Explanations

    referenced ages and time periods related to individuals or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Age followed by "year" or "years"

    np_acts-logits-general · gemini-2.0-flash

    number year old

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AutoScaleMode
    -0.61
    CodedInputStream
    -0.57
    __]
    -0.54
    chkin
    -0.52
    المشاركات
    -0.52
    standes
    -0.50
    dard
    -0.50
    ammlung
    -0.50
    iprot
    -0.49
    hyrchwyd
    -0.49
    POSITIVE LOGITS
    ⓧ
    0.62
     <<<<<<<<<<<<<<
    0.61
    tagHelperRunner
    0.60
    Revenir
    0.54
    EditorBrowsable
    0.52
    führende
    0.52
     Direito
    0.50
    makeConstraints
    0.50
     ExecuteAsync
    0.49
    old
    0.49
    Activations Density 0.132%

    No Known Activations