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. 14322
    Prev
    Next
    INDEX
    Explanations

    statements indicating the presence or absence of evidence or claims in discussions about health-related issues

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

    "There is" / "There is evidence"

    np_acts-logits-general · gemini-2.0-flash

    there is limited 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
     виправивши
    -0.83
    GEBURTSDATUM
    -0.77
    +#+#
    -0.77
     Theſe
    -0.76
    expandindo
    -0.75
     doubtnut
    -0.73
     autorytatywna
    -0.68
     mergeFrom
    -0.68
    ReusableCell
    -0.67
    WindowConstants
    -0.67
    POSITIVE LOGITS
     increasing
    0.52
     no
    0.49
     asimismo
    0.48
    AccessorTable
    0.48
     indications
    0.47
     also
    0.47
     increase
    0.42
    Views
    0.42
     el
    0.42
     belirt
    0.42
    Activations Density 0.188%

    No Known Activations