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. 2932
    Prev
    Next
    INDEX
    Explanations

    terms related to image processing and quantization techniques

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

    technical terms related to image processing, quantization, and bit values.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    numerical values and quantitative measurements in technical contexts.

    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
    ########.
    -0.52
     iprot
    -0.49
    rungsseite
    -0.48
    ➟
    -0.48
    Ἁ
    -0.47
     Collie
    -0.47
     Pill
    -0.47
    :✨
    -0.47
    RemoveField
    -0.47
    conj
    -0.46
    POSITIVE LOGITS
     range
    0.60
     scale
    0.59
     ranges
    0.54
     gray
    0.54
     scales
    0.54
     escala
    0.53
     quantization
    0.52
     scaling
    0.50
    MaxValue
    0.50
     maxValue
    0.47
    Activations Density 0.546%

    No Known Activations