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. 1386
    Prev
    Next
    INDEX
    Explanations

    references to personal possessions and familial relationships

    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
     hecho
    -0.51
    anyika
    -0.45
     городе
    -0.43
    estro
    -0.42
     fact
    -0.41
    čaj
    -0.40
     Affiliations
    -0.39
    estor
    -0.39
     kenyataan
    -0.39
    ("^
    -0.38
    POSITIVE LOGITS
    CloseOperation
    0.76
    ########.
    0.74
    awaiter
    0.69
    BoxShadow
    0.68
    GeoNames
    0.68
     BoxDecoration
    0.65
    Rüyada
    0.59
     препратки
    0.59
    rzost
    0.59
     protoimpl
    0.58
    Activations Density 0.692%

    No Known Activations