© 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-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 16054
    Prev
    Next
    INDEX
    Explanations

    inquiries or prompts for imagination and creativity

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

    the phrase "you can imagine" and related expressions of imagining or conceiving of something.

    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
    GLFW
    -0.35
     Zeichen
    -0.33
     Erkenntnisse
    -0.33
     Ruhm
    -0.33
    SourceChecksum
    -0.32
     estratégica
    -0.31
     Risiken
    -0.31
     Ausrüstung
    -0.31
     Überprüfung
    -0.30
    setDisable
    -0.30
    POSITIVE LOGITS
     imagine
    2.81
     imagining
    2.48
     Imagine
    2.47
    imagine
    2.39
     imagined
    2.39
     imagin
    2.39
     imagines
    2.36
    Imagine
    2.33
     IMAG
    2.28
     imagination
    2.25
    Activations Density 0.441%

    No Known Activations