© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 7766
    Prev
    Next
    INDEX
    Explanations

    technical references to hashing mechanisms and data types in programming

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

    Code, numbers, or date-related text

    np_acts-logits-general · gemini-2.0-flash

    numerical value comparison

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndWait
    -0.34
     Fische
    -0.32
    Additional
    -0.32
    ambilan
    -0.32
    berday
    -0.31
     angek
    -0.31
     indywidual
    -0.31
     igång
    -0.30
     chô
    -0.30
     Additional
    -0.30
    POSITIVE LOGITS
     precision
    0.68
    precision
    0.62
     strconv
    0.59
     representation
    0.56
     representations
    0.55
    IntOverflow
    0.54
     decimal
    0.54
     Signed
    0.54
     فريبيس
    0.53
     précision
    0.52
    Activations Density 1.523%

    No Known Activations