© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 8775
    Prev
    Next
    INDEX
    Explanations

    references to evidence and its implications in various contexts

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

    "evidence"

    np_acts-logits-general · gemini-2.0-flash

    evidence supporting claims

    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
     useRouter
    -0.89
    Tembelea
    -0.73
    ptonshire
    -0.72
    SBATCH
    -0.69
    ✨:
    -0.69
    μός
    -0.69
    Xna
    -0.68
    cipar
    -0.66
    extAlignment
    -0.66
    enumii
    -0.66
    POSITIVE LOGITS
    evidence
    1.40
     Evidence
    1.35
     evidence
    1.34
    Evidence
    1.32
     EVIDENCE
    1.26
     Evid
    1.13
     evidences
    1.11
     preuves
    0.95
     proof
    0.93
     Proof
    0.90
    Activations Density 0.225%

    No Known Activations