© 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. 22-GEMMASCOPE-RES-16K
    11. 8933
    Prev
    Next
    INDEX
    Explanations

    spatial relationships and positions within descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Position or location: front, back, rear, etc

    np_acts-logits-general · gemini-2.0-flash

    spatial directions (front/back/sides)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +:+
    -0.65
    ufig
    -0.50
    ритори
    -0.47
    UseVisualStyle
    -0.45
     Lage
    -0.45
     zapo
    -0.45
    зка
    -0.44
    ệp
    -0.44
     Becher
    -0.44
    ibig
    -0.43
    POSITIVE LOGITS
     front
    1.55
     rear
    1.37
    front
    1.22
     FRONT
    1.17
    rear
    1.12
     back
    1.11
     sides
    1.11
    FRONT
    1.08
     backside
    1.05
     Front
    1.05
    Activations Density 0.287%

    No Known Activations