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. 1002
    Prev
    Next
    INDEX
    Explanations

    language related to professional skills and qualifications

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

    Skills, abilities, or talents

    np_acts-logits-general · gemini-2.0-flash

    skill and abilities

    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
    expandindo
    -0.62
    ruptedException
    -0.49
     BoxFit
    -0.49
    extAlignment
    -0.49
    dou
    -0.46
    greSQL
    -0.45
     epo
    -0.45
    ROUTINE
    -0.44
    abank
    -0.43
    tova
    -0.43
    POSITIVE LOGITS
     skills
    1.99
     skill
    1.88
    skills
    1.69
     Skills
    1.61
    skill
    1.60
     talents
    1.58
     Skill
    1.49
     abilities
    1.46
    Skills
    1.45
     compétences
    1.43
    Activations Density 0.231%

    No Known Activations