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. 10-GEMMASCOPE-RES-16K
    6. 2919
    Prev
    Next
    INDEX
    Explanations

    expressions related to mathematical notation and formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ISupport
    -0.73
    rungsseite
    -0.72
    ⓧ
    -0.69
    ORPG
    -0.68
    rarr
    -0.68
    Бахар
    -0.65
     kasarigan
    -0.65
     AssemblyTitle
    -0.63
    :"-"`
    -0.63
    WireFormat
    -0.63
    POSITIVE LOGITS
    MigrationBuilder
    0.86
     المعيارى
    0.83
    enumi
    0.82
    ########.
    0.80
    Clik
    0.66
     EconPapers
    0.64
    ;#
    0.60
    ValueStyle
    0.57
    évaluateur
    0.55
    MockMvc
    0.54
    Activations Density 0.282%

    No Known Activations