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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 17-GEMMASCOPE-RES-16K
    6. 10822
    Prev
    Next
    INDEX
    Explanations

    instances of the word "for" and expressions related to conditions or considerations affecting multiple parties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MLLoader
    -0.67
     ModelExpression
    -0.55
    diğinde
    -0.55
    ulemon
    -0.53
    MatIconModule
    -0.53
    createTextNode
    -0.50
    +#+
    -0.50
    modb
    -0.49
     kaiser
    -0.48
    ppard
    -0.48
    POSITIVE LOGITS
     us
    0.86
     me
    0.86
     anyone
    0.75
     everyone
    0.74
     everybody
    0.69
    WebVitals
    0.68
     them
    0.65
     anybody
    0.64
    everyone
    0.62
     whoever
    0.61
    Activations Density 0.223%

    No Known Activations