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. 3109
    Prev
    Next
    INDEX
    Explanations

    the concept of serious or severity in various contexts

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

    "serious" or its variants

    np_acts-logits-general · gemini-2.0-flash

    serious accidents, nature, property, works

    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
    multicolumn
    -0.82
    sidemargin
    -0.82
    ReusableCell
    -0.76
     gynhyrchwyd
    -0.74
    LookAnd
    -0.73
    UserScript
    -0.73
    BrowserModule
    -0.71
    INCREF
    -0.70
    ResponseWriter
    -0.69
     disponibilités
    -0.68
    POSITIVE LOGITS
     sério
    0.86
     Serious
    0.85
     serius
    0.81
     seriously
    0.78
     serious
    0.78
    Serious
    0.76
     injury
    0.74
     illness
    0.72
    serious
    0.72
     injured
    0.71
    Activations Density 0.093%

    No Known Activations