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. 6-GEMMASCOPE-RES-16K
    6. 12012
    Prev
    Next
    INDEX
    Explanations

    references to skills and competencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -1.14
    zzlies
    -0.85
    SPARENT
    -0.83
     Commerci
    -0.78
     Fontaine
    -0.77
     Mazar
    -0.75
    djangoproject
    -0.73
    Personensuche
    -0.72
     Mote
    -0.70
     $[-
    -0.70
    POSITIVE LOGITS
     skills
    2.17
     skill
    2.05
    skills
    1.93
     Skills
    1.92
     Skill
    1.90
    Skills
    1.79
    skill
    1.76
    Skill
    1.72
     SKILLS
    1.64
    SKILL
    1.63
    Activations Density 0.057%

    No Known Activations