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. 24-GEMMASCOPE-RES-16K
    6. 14269
    Prev
    Next
    INDEX
    Explanations

    instances of numerical values or counts

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

    Year after a month

    np_acts-logits-general · gemini-2.0-flash

    dates and years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Efq
    -0.90
    InjectAttribute
    -0.89
     وتسجيلات
    -0.84
    httphttps
    -0.82
    ConstraintMaker
    -0.79
     houſe
    -0.79
     المعيارى
    -0.78
     reaſon
    -0.76
     ſtate
    -0.72
     Jefus
    -0.71
    POSITIVE LOGITS
    8
    1.00
    9
    1.00
    7
    1.00
    6
    0.95
    5
    0.89
    4
    0.88
    0
    0.88
    3
    0.84
    2
    0.74
    1
    0.70
    Activations Density 0.090%

    No Known Activations