© 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. 5-GEMMASCOPE-RES-16K
    11. 3267
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate difficulty or complexity in tasks and comparisons to trivial matters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    #+#
    -0.69
    Παραπομπές
    -0.68
     surla
    -0.65
     ffilmiau
    -0.60
     psycopg
    -0.60
    BufferException
    -0.59
     بيها
    -0.59
     "..\..\..\
    -0.58
    DispatchToProps
    -0.58
    NUMX
    -0.58
    POSITIVE LOGITS
     nor
    0.59
    nor
    0.55
    وف
    0.48
    $',
    0.48
     indeed
    0.47
    WICH
    0.46
    :]:
    0.46
    ()]);
    0.46
    BoxShadow
    0.46
     hề
    0.45
    Activations Density 0.170%

    No Known Activations