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. 22-GEMMASCOPE-RES-16K
    6. 13877
    Prev
    Next
    INDEX
    Explanations

    references to professional roles and membership in organizations

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

    being in charge or serving

    np_acts-logits-general · gemini-2.0-flash

    role and action verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uxxxx
    -0.64
     beginnetje
    -0.61
    клопе
    -0.60
    COUVER
    -0.57
    findpost
    -0.53
    KeySpec
    -0.52
    verwijspagina
    -0.51
    󠁿
    -0.51
    Trax
    -0.50
    riebenen
    -0.50
    POSITIVE LOGITS
     active
    0.85
     serving
    0.82
     serve
    0.81
     chairman
    0.81
     chaired
    0.79
     aktif
    0.79
     served
    0.78
     chair
    0.78
     volunteer
    0.77
     serves
    0.76
    Activations Density 0.114%

    No Known Activations