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

    Neuronpedia

    APICircuit 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. 10255
    Prev
    Next
    INDEX
    Explanations

    emotions related to dissatisfaction and distress

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     GenerationType
    -0.72
    ]")]
    -0.64
    uxxxx
    -0.63
    MENAFN
    -0.63
    ContextHolder
    -0.61
     GoogleFonts
    -0.61
    requireNonNull
    -0.61
    migrationBuilder
    -0.60
    InvalidProtocol
    -0.60
    >");
    
    -0.59
    POSITIVE LOGITS
     seeing
    0.92
     about
    0.85
     realizing
    0.67
     because
    0.67
    Seeing
    0.67
    看到
    0.67
    seeing
    0.66
     увиде
    0.65
     Seeing
    0.65
     realising
    0.64
    Activations Density 0.203%

    No Known Activations