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. 21-GEMMASCOPE-RES-16K
    6. 7363
    Prev
    Next
    INDEX
    Explanations

    the presence of specific terms related to unique identifiers, particularly within the context of observational or experimental data related to infectious agents or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IBOutlet
    -0.65
    WithEmail
    -0.56
     متعلقه
    -0.55
    ื่อง
    -0.52
    }));
    
    -0.52
     "<?
    -0.52
    ваемых
    -0.51
    imų
    -0.51
     ***!
    -0.51
     healthy
    -0.51
    POSITIVE LOGITS
     Paren
    0.63
    CodedInputStream
    0.61
     Pauli
    0.59
     дописавши
    0.58
     Abp
    0.58
    tvguidetime
    0.57
     peony
    0.57
    stateParams
    0.57
     createSprite
    0.56
     Opa
    0.56
    Activations Density 0.096%

    No Known Activations