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. 7-GEMMASCOPE-RES-16K
    6. 4615
    Prev
    Next
    INDEX
    Explanations

    descriptions and references to human eyes and their expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⓧ
    -0.76
    tonsoft
    -0.72
    txtName
    -0.65
    devils
    -0.64
    apunov
    -0.61
    makeatother
    -0.60
    Datuak
    -0.60
    XtraReports
    -0.59
    ритори
    -0.59
     HFILL
    -0.58
    POSITIVE LOGITS
     eyes
    0.96
     Eyes
    0.84
    Eyes
    0.81
    eyes
    0.74
     EYES
    0.73
     ojos
    0.67
     occhi
    0.65
     eye
    0.62
     چش
    0.60
     gaze
    0.58
    Activations Density 0.110%

    No Known Activations