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. 12-GEMMASCOPE-RES-16K
    6. 14629
    Prev
    Next
    INDEX
    Explanations

    symbolic representations, particularly those involving quotes and special characters

    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
    SequentialGroup
    -0.61
     estekak
    -0.52
     poveznice
    -0.52
    copg
    -0.52
     kaarangay
    -0.49
    ">*</
    -0.46
    zygous
    -0.46
    newArrayList
    -0.45
    nloa
    -0.45
     Akismet
    -0.45
    POSITIVE LOGITS
    XmlEnum
    0.67
    MigrationBuilder
    0.65
    Халык
    0.58
     Meksiku
    0.57
    éndolo
    0.55
    יצוני
    0.55
    endphp
    0.54
    InlineData
    0.53
    contentLoaded
    0.53
    <?,
    0.52
    Activations Density 0.726%

    No Known Activations