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. 12-GEMMASCOPE-RES-16K
    6. 4612
    Prev
    Next
    INDEX
    Explanations

    references to relationships and their dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gaj
    -0.85
     citoy
    -0.80
     sanitarias
    -0.78
     policiales
    -0.76
     Cellulose
    -0.75
     scheda
    -0.75
    TNode
    -0.74
     polaire
    -0.74
     espirituales
    -0.74
     nationaux
    -0.74
    POSITIVE LOGITS
     relationships
    1.88
     relationship
    1.86
    Relationships
    1.58
     Relationship
    1.57
     Relationships
    1.52
    relationships
    1.47
    Relationship
    1.44
    relationship
    1.40
     relations
    1.34
     RELATIONSHIP
    1.31
    Activations Density 0.077%

    No Known Activations