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. 12684
    Prev
    Next
    INDEX
    Explanations

    terms related to drilling operations and their effectiveness in soil treatment

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

    preceding "cycle", "reaction", "attempt", "day", or "iteration"

    np_acts-logits-general · gemini-2.0-flash

    single event, step, or session

    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
    IntoConstraints
    -0.82
    ThroughAttribute
    -0.58
     defaultstate
    -0.57
     []:
    -0.53
    reszcie
    -0.53
     مرئيه
    -0.50
    )$/,
    -0.48
     rayures
    -0.48
     spectateurs
    -0.47
     locaux
    -0.47
    POSITIVE LOGITS
     session
    1.23
     cycle
    1.15
     round
    1.12
     rounds
    1.04
     sessions
    1.03
     cycles
    1.01
     pass
    0.98
    session
    0.94
     run
    0.94
     Session
    0.91
    Activations Density 0.598%

    No Known Activations