© 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. 9678
    Prev
    Next
    INDEX
    Explanations

    instances of confusion or misunderstanding in various contexts

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

    instances of the word "confusion" or closely related concepts of ambiguity and bewilderment.

    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
    DebuggerNonUser
    -0.39
    styleType
    -0.38
    resizingMask
    -0.37
     ép
    -0.37
     '\\;'
    -0.36
    OGND
    -0.35
     gawas
    -0.34
     cime
    -0.33
     unthinkable
    -0.33
    Недостатки
    -0.33
    POSITIVE LOGITS
     confusion
    2.58
     confused
    2.41
     confusing
    2.34
     confuses
    2.28
     confuse
    2.28
     Confusion
    2.23
     confusión
    2.17
    Confusion
    2.16
     Confused
    2.16
    Confused
    2.11
    Activations Density 0.652%

    No Known Activations