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. 4-GEMMASCOPE-RES-16K
    6. 15917
    Prev
    Next
    INDEX
    Explanations

    references to future events, particularly the concept of "tomorrow."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ThemeData
    -0.86
    encodeWith
    -0.75
    uji
    -0.73
     AssemblyTitle
    -0.70
    WebControls
    -0.70
    WritableDatabase
    -0.69
     useHistory
    -0.69
    ்கள்
    -0.68
    بوابة
    -0.67
     useParams
    -0.67
    POSITIVE LOGITS
     tomorrow
    1.75
    ORROW
    1.58
    tomorrow
    1.51
    Tomorrow
    1.39
     Tomorrow
    1.35
     domani
    1.30
     demain
    1.19
     amanhã
    1.15
    morrow
    1.06
     morrow
    0.96
    Activations Density 0.090%

    No Known Activations