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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 5-GEMMASCOPE-RES-16K
    6. 10477
    Prev
    Next
    INDEX
    Explanations

    elements related to emotional experiences and psychological states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    httphttps
    -0.86
     للمعارف
    -0.71
     ExecuteAsync
    -0.70
     lingue
    -0.65
    DialogContent
    -0.63
    SYMBOL
    -0.61
    enderror
    -0.61
    openhague
    -0.61
    strains
    -0.60
    MigrationBuilder
    -0.60
    POSITIVE LOGITS
    PhysRev
    0.45
    enerys
    0.42
    wahati
    0.42
    estens
    0.40
    Uninitialized
    0.40
     writeTo
    0.40
     NavController
    0.39
     stessa
    0.39
    kově
    0.39
    ReadInt
    0.39
    Activations Density 0.801%

    No Known Activations