Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15682
    Prev
    Next
    INDEX
    Explanations

    phrases related to movement and direction

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

    Directional movement: "up," "down," or "out"

    np_acts-logits-general · gemini-2.0-flash

    directional movement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    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
    expandindo
    -0.70
     ddelweddau
    -0.60
    adaptiveStyles
    -0.60
    RenderAtEndOf
    -0.57
    GEBURTSDATUM
    -0.57
    /*!
    -0.53
    VIAF
    -0.53
     
    -0.52
    Geplaatst
    -0.51
     propOrder
    -0.51
    POSITIVE LOGITS
     toward
    0.49
     into
    0.49
    toward
    0.47
    wards
    0.44
     towards
    0.44
     onto
    0.41
    into
    0.41
    towards
    0.39
     Mesmo
    0.37
    Toward
    0.34
    Activations Density 0.166%

    No Known Activations