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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 3-GEMMASCOPE-RES-16K
    6. 6408
    Prev
    Next
    INDEX
    Explanations

    the occurrence of copyright and licensing terms in documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ResponseEntity
    -0.94
    mybatisplus
    -0.83
     @"/
    -0.80
    
    -0.76
    WebMethod
    -0.73
     axios
    -0.72
    MediaStore
    -0.69
    SharedCtor
    -0.67
    Autoritní
    -0.67
     snippetHide
    -0.65
    POSITIVE LOGITS
     MonoBehaviour
    1.36
    UseVisualStyle
    1.11
    describe
    0.97
    bootstrap
    0.82
     evt
    0.81
    GetComponent
    0.71
     reserved
    0.67
     OnInit
    0.62
     GetComponent
    0.61
    styleUrls
    0.60
    Activations Density 0.014%

    No Known Activations