© 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. 37-GEMMASCOPE-RES-16K
    11. 4284
    Prev
    Next
    INDEX
    Explanations

    references to personal choices and responsibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyTitle
    -0.66
     surla
    -0.65
    HostException
    -0.60
     Meksiku
    -0.59
    帖最后由
    -0.58
     AssemblyVersion
    -0.57
     Signalez
    -0.57
    InstrumentedTest
    -0.56
    queryInterface
    -0.55
    ConstraintMaker
    -0.55
    POSITIVE LOGITS
     owe
    0.67
     owes
    0.60
     cannot
    0.50
     mustn
    0.45
     can
    0.42
     owed
    0.42
     shouldn
    0.42
     alone
    0.41
     too
    0.41
     needn
    0.39
    Activations Density 0.416%

    No Known Activations