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. 16291
    Prev
    Next
    INDEX
    Explanations

    references to individuals involved in legal or judicial proceedings

    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
     виправивши
    -0.88
    +#+#
    -0.72
    OGND
    -0.65
     AssemblyCulture
    -0.61
     mág
    -0.59
    TagHelper
    -0.58
    škin
    -0.57
    verwijspagina
    -0.55
     curiosidad
    -0.55
     científicas
    -0.54
    POSITIVE LOGITS
     also
    0.89
     had
    0.67
     spent
    0.64
     not
    0.64
     said
    0.62
    '
    0.60
     then
    0.57
     همچنین
    0.56
    ’
    0.55
     never
    0.54
    Activations Density 0.385%

    No Known Activations