© 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. 11-GEMMASCOPE-RES-16K
    11. 8505
    Prev
    Next
    INDEX
    Explanations

    references to height, elevation, and positioning in a physical or metaphorical space

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    marginHorizontal
    -0.50
    <eos>
    -0.46
    hosa
    -0.43
     lane
    -0.42
    mphony
    -0.42
    outh
    -0.42
    市镇
    -0.41
    addGroup
    -0.41
     direct
    -0.41
    று
    -0.41
    POSITIVE LOGITS
     heights
    1.46
     height
    1.26
     Height
    1.16
     tallest
    1.15
     raiſ
    1.14
    Heights
    1.11
     elevation
    1.10
     getHeight
    1.10
     HEIGHT
    1.09
     Heights
    1.08
    Activations Density 0.585%

    No Known Activations