© 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. 5881
    Prev
    Next
    INDEX
    Explanations

    variable declarations related to currency, destination, and flight details in programming contexts

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

    Code tokens and special characters

    np_acts-logits-general · gemini-2.0-flash

    ._exported programming constructs

    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
    DotNetBar
    -0.45
    EndInit
    -0.42
    ruptedException
    -0.42
     سكانية
    -0.41
    ectady
    -0.41
    XmlAccessType
    -0.40
    Maka
    -0.39
     Meksiku
    -0.38
    gdx
    -0.38
    reactstrap
    -0.38
    POSITIVE LOGITS
    GOTREF
    0.56
    帖最后由
    0.50
     >=",
    0.50
     uLocal
    0.47
     ***!
    0.44
    richTextPanel
    0.41
     aimé
    0.40
     öyle
    0.40
    Gods
    0.40
     adhesivo
    0.40
    Activations Density 0.484%

    No Known Activations