© 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. 24-GEMMASCOPE-RES-16K
    6. 5212
    Prev
    Next
    INDEX
    Explanations

    structure and syntax patterns in programming or data declaration code

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

    "case" keyword within code

    np_acts-logits-general · gemini-2.0-flash

    case followed by try

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    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
    MLLoader
    -0.50
    expandindo
    -0.49
     strerror
    -0.49
    HasForeignKey
    -0.47
    AntiForgeryToken
    -0.46
     surla
    -0.46
     groupBox
    -0.45
    IVEREF
    -0.45
    новништво
    -0.44
    POSITIVE LOGITS
    return
    0.41
     SHO
    0.40
    sho
    0.40
    ese
    0.40
    break
    0.39
    case
    0.39
     falls
    0.39
    SHO
    0.38
    MM
    0.37
    Falling
    0.36
    Activations Density 0.393%

    No Known Activations