© 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-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 9035
    Prev
    Next
    INDEX
    Explanations

    references to locations and orientations of objects, particularly in relation to their 'top', 'bottom', 'rear', and 'front' aspects

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

    spatial positioning words referring to the rear or back of objects.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⤹
    -0.48
     ControllerBase
    -0.36
     backed
    -0.35
    DotNetBar
    -0.34
    ревно
    -0.34
    ทาง
    -0.33
     الساعة
    -0.33
    TableAdapter
    -0.33
    Publisher
    -0.32
     znam
    -0.32
    POSITIVE LOGITS
    most
    0.64
     portion
    0.63
     EconPapers
    0.56
    MOST
    0.55
    SequentialGroup
    0.53
    Portail
    0.52
     Portion
    0.52
     consultato
    0.52
     дописавши
    0.50
    portion
    0.47
    Activations Density 0.300%

    No Known Activations