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. 13457
    Prev
    Next
    INDEX
    Explanations

    the names and roles of characters in films and theatrical productions

    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
    >--}}
    -0.84
    "}")
    -0.81
    --}}
    -0.73
    !")
    
    -0.72
    */)
    -0.71
    "):
    
    -0.69
     ISNI
    -0.69
    >-->
    -0.69
     preserve
    -0.67
     propOrder
    -0.67
    POSITIVE LOGITS
    役
    0.51
    AutoScale
    0.50
     OMITTED
    0.47
    parsedMessage
    0.46
    hasErrors
    0.44
    ContentAlignment
    0.43
     culturelles
    0.43
    printStackTrace
    0.41
    (
    0.41
     CanadaChoose
    0.40
    Activations Density 0.244%

    No Known Activations