© 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-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 13693
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "turn" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.89
     hjemmeside
    -0.81
     CURIAM
    -0.78
     veckan
    -0.78
     weihnachten
    -0.77
     ProtoMessage
    -0.77
    MemoryWarning
    -0.77
    esez
    -0.76
     neceff
    -0.76
    horabuena
    -0.76
    POSITIVE LOGITS
     turn
    2.34
     TURN
    2.25
     Turn
    2.25
    Turn
    2.18
     turned
    2.08
     turns
    2.07
    TURN
    2.04
    turn
    2.01
    Turned
    1.92
     turning
    1.91
    Activations Density 0.050%

    No Known Activations