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. 18-GEMMASCOPE-RES-16K
    6. 10422
    Prev
    Next
    INDEX
    Explanations

    evidence and legal terms related to court proceedings and contractual obligations

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

    "evidence"

    np_acts-logits-general · gemini-2.0-flash

    facts and evidence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bootstrapcdn
    -0.70
     незавершена
    -0.65
    paravant
    -0.62
    Handle
    -0.61
    
    -0.61
     prediction
    -0.59
    opsida
    -0.59
     nakalista
    -0.59
     Prediction
    -0.58
     Predictions
    -0.56
    POSITIVE LOGITS
     evidence
    0.76
    evidence
    0.67
    Evidence
    0.63
     EVIDENCE
    0.62
     evi
    0.62
    awtextra
    0.58
     testimony
    0.56
     Evidence
    0.53
     witnesses
    0.52
     '\\;'
    0.51
    Activations Density 2.080%

    No Known Activations