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. 2-GEMMASCOPE-RES-16K
    6. 6344
    Prev
    Next
    INDEX
    Explanations

    references to strategic plans or planning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Hauptartikel
    -0.68
    enderror
    -0.67
    bibfield
    -0.67
    fromCharCode
    -0.67
    URED
    -0.65
    amazonaws
    -0.64
    ICATED
    -0.64
    produzione
    -0.63
    Quanto
    -0.63
     resourceCulture
    -0.63
    POSITIVE LOGITS
     plan
    3.96
     Plan
    3.84
    plan
    3.74
    Plan
    3.68
     PLAN
    3.62
    PLAN
    3.15
     plans
    3.13
     Plans
    3.03
    plans
    2.93
    Plans
    2.78
    Activations Density 0.083%

    No Known Activations