© 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. 25-GEMMASCOPE-RES-16K
    11. 2924
    Prev
    Next
    INDEX
    Explanations

    structured data representations and control flow constructs in programming

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

    key programming constructs, particularly related to data structure definitions and control flow statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ');
    -0.45
    ");
    -0.42
    Poloha
    -0.41
    angg
    -0.41
    .”)
    -0.41
    !");
    -0.40
    ”).
    -0.40
    ”)
    -0.39
    >());
    -0.39
    !");
    -0.38
    POSITIVE LOGITS
    case
    2.02
     case
    1.98
     Case
    1.49
    Case
    1.46
     cases
    1.42
     CASE
    1.34
    CASE
    1.34
     caso
    1.32
    break
    1.23
     Cases
    1.21
    Activations Density 0.145%

    No Known Activations