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 - 65k
    5. 12-GEMMASCOPE-RES-65K
    6. 43441
    Prev
    Next
    INDEX
    Explanations

    the presence of the text marker "<bos>", indicating the beginning of a sequence or segment

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    StoryboardSegue
    -0.56
    msgTypes
    -0.56
     Remarque
    -0.48
     stoppen
    -0.47
    PushMatrix
    -0.46
     disponibilité
    -0.46
     Mérimée
    -0.45
    CreateModel
    -0.44
     invented
    -0.43
    Cyfarwyddwr
    -0.42
    POSITIVE LOGITS
     يتيمه
    0.95
    Portale
    0.86
     Roskov
    0.79
    Hozzáférés
    0.76
    sonder
    0.72
     TextInputType
    0.69
    سطس
    0.68
     jadx
    0.66
     محفوظة
    0.65
    Geplaatst
    0.65
    Activations Density 0.002%

    No Known Activations