© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 6757
    Prev
    Next
    INDEX
    Explanations

    instances of decision-making or choices made

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

    "decided" and its context

    np_acts-logits-general · gemini-2.0-flash

    the act of deciding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    marginHorizontal
    -0.49
     the
    -0.47
    @
    -0.46
     nabíz
    -0.43
    Throughout
    -0.42
     images
    -0.42
     @
    -0.42
     Whit
    -0.41
    lang
    -0.41
     her
    -0.41
    POSITIVE LOGITS
    Decide
    1.08
    decide
    1.08
     Decide
    1.04
     decide
    1.01
    decision
    0.97
     decided
    0.96
     decides
    0.96
     decision
    0.95
    decided
    0.95
     Decision
    0.94
    Activations Density 0.124%

    No Known Activations