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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 13-GEMMASCOPE-RES-65K
    6. 15112
    Prev
    Next
    INDEX
    Explanations

    text that starts with the "<bos>" token, indicating the beginning of a new segment or context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     favor
    -0.52
     and
    -0.49
    ujan
    -0.48
     e
    -0.47
     or
    -0.46
    ács
    -0.44
     parlé
    -0.44
    anye
    -0.44
     try
    -0.42
     favorite
    -0.42
    POSITIVE LOGITS
    GEBURTSDATUM
    0.85
     estimés
    0.78
     estekak
    0.77
     disambiguazione
    0.77
     Meksiku
    0.77
    ########.
    0.74
    ]")]
    0.72
     ligiloj
    0.71
    Personensuche
    0.70
    StoryboardSegue
    0.70
    Activations Density 0.046%

    No Known Activations