© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 7879
    Prev
    Next
    INDEX
    Explanations

    terms related to healthcare and medical conditions

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

    Immediately precedes words like 'related' or 'based'

    np_acts-logits-general · gemini-2.0-flash

    -related, -based, -dependent, -induced

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    \{\\
    -0.65
    Unfinished
    -0.59
    TagMode
    -0.50
     Lordships
    -0.48
    complexType
    -0.47
    StackNavigator
    -0.46
    iciens
    -0.46
    ICLES
    -0.46
    antası
    -0.45
    bangan
    -0.45
    POSITIVE LOGITS
     related
    1.60
     based
    1.42
     oriented
    1.41
    related
    1.39
    based
    1.37
     driven
    1.35
     centric
    1.27
     Related
    1.25
     RELATED
    1.20
    Based
    1.15
    Activations Density 1.523%

    No Known Activations