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 - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 6796
    Prev
    Next
    INDEX
    Explanations

    the term "utils" in various contexts, related to utility functions or classes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     &___
    -0.65
     calendriers
    -0.61
     Wicidata
    -0.60
    Datuak
    -0.58
    offset
    -0.53
    Vidite
    -0.52
    Roma
    -0.52
    __":
    -0.51
     impegno
    -0.50
    GoogleApiClient
    -0.50
    POSITIVE LOGITS
     rowspan
    3.77
    multirow
    1.50
    multicolumn
    0.83
     colspan
    0.78
    醐
    0.76
     Chwiliwch
    0.73
    AddHtmlAttribute
    0.73
    ."],
    0.71
     wireType
    0.67
    .[/
    0.64
    Activations Density 0.030%

    No Known Activations