© 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. 40-GEMMASCOPE-RES-16K
    11. 2072
    Prev
    Next
    INDEX
    Explanations

    terms related to correctness and propriety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     successfully
    -0.45
    success
    -0.44
     better
    -0.43
     favorable
    -0.43
     /\.
    -0.43
     факт
    -0.42
     favorably
    -0.42
    successfully
    -0.42
     successful
    -0.41
    DrawerLayout
    -0.41
    POSITIVE LOGITS
     timing
    0.81
     sized
    0.71
     balance
    0.70
     proportions
    0.68
     amount
    0.67
    sized
    0.63
     combination
    0.63
     placement
    0.63
     dosage
    0.60
     Timing
    0.59
    Activations Density 0.545%

    No Known Activations