© 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. 1-GEMMASCOPE-RES-16K
    11. 9060
    Prev
    Next
    INDEX
    Explanations

    terms related to depth, particularly in the context of depth perception or representation in imaging

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ArrowToggle
    -0.70
    walde
    -0.62
    Географи
    -0.62
     Gell
    -0.61
    malink
    -0.60
    imageshack
    -0.58
    canyon
    -0.58
     Ibid
    -0.58
    Strong
    -0.57
    Ivoire
    -0.56
    POSITIVE LOGITS
     depth
    1.75
    Depth
    1.66
     DEPTH
    1.56
     Depth
    1.55
    depth
    1.55
    DEPTH
    1.38
     depths
    1.10
     profundidad
    0.98
    dep
    0.97
    深度
    0.96
    Activations Density 0.069%

    No Known Activations