© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 13205
    Prev
    Next
    INDEX
    Explanations

    phrases related to directions and guidance

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

    preceding "direction"

    np_acts-logits-general · gemini-2.0-flash

    direction specified by qualifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     оригіналу
    -0.47
    Args
    -0.41
     pozn
    -0.41
     lazo
    -0.40
    Raised
    -0.39
    awan
    -0.39
    μει
    -0.39
     Raised
    -0.39
    صالات
    -0.38
     mág
    -0.36
    POSITIVE LOGITS
     direction
    2.73
     Direction
    2.33
     directions
    2.27
    direction
    2.25
     DIRECTION
    2.15
    Direction
    2.07
    directions
    1.92
     Directions
    1.89
    方向
    1.86
     direção
    1.83
    Activations Density 0.289%

    No Known Activations