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. 11-GEMMASCOPE-RES-16K
    6. 7181
    Prev
    Next
    INDEX
    Explanations

    concepts related to structural integrity and evaluation in research methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.60
    abestanden
    -0.54
     kaarangay
    -0.53
    RegistryLite
    -0.53
    DoubleQuotes
    -0.52
     насељу
    -0.51
     esternos
    -0.48
     noqa
    -0.47
     виправивши
    -0.47
     tartalomajánló
    -0.46
    POSITIVE LOGITS
    XmlAccessType
    0.74
    matchCondition
    0.67
     >=",
    0.67
    bootstrapcdn
    0.65
    IsContent
    0.62
     '\\;'
    0.62
    UnsafeEnabled
    0.62
     TextInputType
    0.60
    BuilderFactory
    0.59
    inaison
    0.58
    Activations Density 0.772%

    No Known Activations