© 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. 2710
    Prev
    Next
    INDEX
    Explanations

    negations and expressions of uncertainty or disagreement

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

    negations and denials using the word "not".

    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
     AssemblyTitle
    -0.74
     GenerationType
    -0.74
    ThroughAttribute
    -0.72
    UrlResolution
    -0.70
    IntoConstraints
    -0.68
    parsedMessage
    -0.65
    ConstraintMaker
    -0.65
    رشف
    -0.65
     <=",
    -0.64
    Geplaatst
    -0.61
    POSITIVE LOGITS
     magically
    0.63
     necessarily
    0.53
     suddenly
    0.50
     magic
    0.48
     automatically
    0.42
     magical
    0.41
     exclusive
    0.40
     miraculously
    0.40
     exclusively
    0.40
     any
    0.39
    Activations Density 0.634%

    No Known Activations