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. 4336
    Prev
    Next
    INDEX
    Explanations

    terms associated with accusations and suspicions of criminal activity

    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
     viewDidLoad
    -0.75
    ContentAsync
    -0.69
    tableFuture
    -0.67
     Audiodateien
    -0.65
     समीक्षाएं
    -0.65
    ulemon
    -0.61
    orsese
    -0.61
    terus
    -0.60
    Біографія
    -0.59
    utnik
    -0.59
    POSITIVE LOGITS
     suspected
    1.55
     suspect
    1.53
     accuse
    1.50
     accused
    1.48
     suspects
    1.43
     accuses
    1.39
     accusing
    1.32
     suspicion
    1.31
     accusations
    1.19
     suspe
    1.15
    Activations Density 0.221%

    No Known Activations