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. 15-GEMMASCOPE-RES-16K
    6. 12814
    Prev
    Next
    INDEX
    Explanations

    phrases associated with emotional or psychological turmoil and the impact of external influences on individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ilkan
    -0.36
     portée
    -0.35
    enzi
    -0.35
     lieb
    -0.35
     ogóle
    -0.34
    роваться
    -0.34
    bör
    -0.33
     rechange
    -0.33
                                  
    -0.33
     portata
    -0.33
    POSITIVE LOGITS
    RenderAtEndOf
    0.92
    MigrationBuilder
    0.84
    ThroughAttribute
    0.83
    IntoConstraints
    0.80
    AndEndTag
    0.76
     mergeFrom
    0.73
    bootstrapcdn
    0.73
    posedge
    0.73
     يتيمه
    0.71
     informée
    0.69
    Activations Density 0.391%

    No Known Activations