Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 14606
    Prev
    Next
    INDEX
    Explanations

    references to the concept of 'people' or groups of individuals

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

    "People" or its variations

    np_acts-logits-general · gemini-2.0-flash

    people followed by v or for

    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
    ArgsConstructor
    -0.76
    AddTagHelper
    -0.73
    AnchorStyles
    -0.70
    istoitu
    -0.69
     للمعارف
    -0.69
     RouterModule
    -0.65
    Typo
    -0.65
     Bort
    -0.63
    phem
    -0.62
     Bless
    -0.62
    POSITIVE LOGITS
     People
    0.98
    People
    0.96
     PEOPLE
    0.96
    PEOPLE
    0.96
     people
    0.92
    people
    0.91
    tvguidetime
    0.84
     who
    0.84
     peoples
    0.55
    ThroughAttribute
    0.55
    Activations Density 0.198%

    No Known Activations