© 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. 15142
    Prev
    Next
    INDEX
    Explanations

    the action of turning or changing direction

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

    "turn" or its variations

    np_acts-logits-general · gemini-2.0-flash

    turn followed by words like to, out, over

    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
     femininas
    -0.54
     EVA
    -0.53
    IntoConstraints
    -0.52
     fapt
    -0.52
     gerek
    -0.51
    ervlak
    -0.51
     préférable
    -0.51
    makeConstraints
    -0.50
     Wulf
    -0.50
    hasMoreElements
    -0.50
    POSITIVE LOGITS
     TURN
    1.49
     Turn
    1.48
     turn
    1.48
    TURN
    1.47
     turns
    1.42
    Turn
    1.42
     turned
    1.36
    Turning
    1.36
     turning
    1.35
    Turned
    1.35
    Activations Density 0.062%

    No Known Activations