© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 1303
    Prev
    Next
    INDEX
    Explanations

    phrases expressing hope and well-wishing sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dflare
    -0.66
     imper
    -0.64
    principalColumn
    -0.59
     Imperium
    -0.58
    terase
    -0.58
    matchCondition
    -0.58
    __":
    -0.57
    CJK
    -0.55
    ♥♥
    -0.55
    (&:
    -0.54
    POSITIVE LOGITS
     HOPE
    1.25
     Hopes
    1.15
     Hope
    1.15
     hopes
    1.13
     hope
    1.12
    HOPE
    1.10
    hope
    1.10
    Hope
    1.06
     hoped
    0.99
     hoping
    0.99
    Activations Density 0.074%

    No Known Activations