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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 17-GEMMASCOPE-RES-16K
    11. 338
    Prev
    Next
    INDEX
    Explanations

    plans and strategies related to actions and decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enderror
    -0.54
    principalTable
    -0.47
    Gweler
    -0.46
     voorbij
    -0.45
    ớt
    -0.43
    HomeAsUpEnabled
    -0.42
    cipta
    -0.41
     كومونز
    -0.41
     vorbei
    -0.40
     anerkannt
    -0.40
    POSITIVE LOGITS
     plan
    2.49
    plan
    2.13
     plans
    2.07
     Plan
    2.05
    Plan
    1.93
     PLAN
    1.89
     Plans
    1.85
    plans
    1.85
     strategy
    1.80
    Plans
    1.80
    Activations Density 0.286%

    No Known Activations