Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 9397
    Prev
    Next
    INDEX
    Explanations

    action verbs associated with movement and escape

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

    words describing rapid or purposeful movement, particularly verbs like walked, ran, drove, sprinted, and glided.

    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
    BagLayout
    -0.52
    ngdoc
    -0.49
    StructEnd
    -0.46
    IntoConstraints
    -0.45
    SpringBootTest
    -0.44
    Yaw
    -0.44
     المعيارى
    -0.43
    存于互联网档案馆
    -0.42
     OFDb
    -0.42
    Javadoc
    -0.42
    POSITIVE LOGITS
     through
    0.97
     toward
    0.86
     across
    0.85
     towards
    0.84
     past
    0.79
     down
    0.74
     along
    0.73
     gennem
    0.68
     forward
    0.68
     around
    0.66
    Activations Density 0.421%

    No Known Activations