© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 14963
    Prev
    Next
    INDEX
    Explanations

    key components related to reasoning and motivation in a narrative

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

    the noun or person that is being described or characterized as the main subject of a sentence.

    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
    MENAFN
    -0.49
    cody
    -0.38
    viewWillAppear
    -0.34
    XmlAccessType
    -0.34
    propTypes
    -0.34
    ThemeOverlay
    -0.34
    apad
    -0.33
    ToBounds
    -0.32
    Filmographie
    -0.32
    IntoConstraints
    -0.31
    POSITIVE LOGITS
     behind
    3.47
    behind
    3.05
     Behind
    2.97
    Behind
    2.92
     BEHIND
    2.72
     detrás
    2.69
     derrière
    2.48
     dietro
    2.33
     bakom
    2.19
     achter
    1.77
    Activations Density 0.497%

    No Known Activations