Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 1756
    Prev
    Next
    INDEX
    Explanations

    instances of negation or expressions of refusal

    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
    İstinadlar
    -0.73
    AutoScaleMode
    -0.69
     Chrift
    -0.64
     Jefus
    -0.64
    AddTagHelper
    -0.63
    Референце
    -0.62
    Sucesor
    -0.62
     Efq
    -0.59
     BorderRadius
    -0.58
    rsiniz
    -0.58
    POSITIVE LOGITS
    RegistryLite
    0.57
    databind
    0.56
    ivir
    0.56
    .’
    0.55
    Pump
    0.54
    )’
    0.52
    rouvez
    0.51
     Ather
    0.49
    s
    0.49
    $_['
    0.49
    Activations Density 0.056%

    No Known Activations