© 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. 564
    Prev
    Next
    INDEX
    Explanations

    formatted output statements and error handling in programming context

    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
    انجليز
    -0.53
    fhir
    -0.49
    \_
    -0.49
    ̣
    -0.48
    \_\_
    -0.48
    ienda
    -0.47
    脚注の使い方
    -0.44
     Sputnik
    -0.44
     Daven
    -0.43
    kesha
    -0.43
    POSITIVE LOGITS
     %
    2.52
    %
    2.30
    .%
    2.18
    :%
    2.13
    /%
    2.11
    ,%
    2.09
    >%
    2.09
     (%
    2.08
    (%
    2.06
    =%
    2.05
    Activations Density 0.358%

    No Known Activations