© 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-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 6042
    Prev
    Next
    INDEX
    Explanations

    higher activation values associated with programming or coding constructs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     HasFactory
    -0.81
     @"/
    -0.77
     cherchés
    -0.77
    AddTagHelper
    -0.77
    ⓧ
    -0.77
    Jeografia
    -0.74
    XmlAccessType
    -0.71
    __':
    -0.71
    цездатний
    -0.71
     /\.(
    -0.69
    POSITIVE LOGITS
    upassen
    0.48
     Willem
    0.45
     względu
    0.44
    Filmographie
    0.44
    Kabel
    0.42
    artet
    0.42
    نمای
    0.42
    èt
    0.41
    OMB
    0.41
    withstanding
    0.40
    Activations Density 0.074%

    No Known Activations