© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 1763
    Prev
    Next
    INDEX
    Explanations

    conditional statements and error handling constructs in programming code

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

    Code, errors, and string formatting

    np_acts-logits-general · gemini-2.0-flash

    Java string and type checking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ujednoznacz
    -0.72
    AutoScaleMode
    -0.63
    basicConfig
    -0.59
     ElementRef
    -0.59
    antMatchers
    -0.58
    WireFormatLite
    -0.57
    XmlRootElement
    -0.56
    SharedDtor
    -0.56
    endphp
    -0.55
     AppComponent
    -0.54
    POSITIVE LOGITS
    String
    0.63
    string
    0.63
     String
    0.61
     string
    0.57
    expandindo
    0.52
     udaler
    0.51
    intahan
    0.50
     GenerationType
    0.50
    intah
    0.49
     通販
    0.47
    Activations Density 0.063%

    No Known Activations