Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 3032
    Prev
    Next
    INDEX
    Explanations

    adjectives that describe the quality or effectiveness of various subjects or actions

    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
     betweenstory
    -1.21
    RegressionTest
    -0.92
    LookAnd
    -0.89
    AndEndTag
    -0.89
    TypedDataSet
    -0.82
    GEBURTSDATUM
    -0.81
    YourGuide
    -0.80
    MessageOf
    -0.80
    enderror
    -0.80
    حوالہ
    -0.77
    POSITIVE LOGITS
     enough
    1.14
    enough
    0.69
     to
    0.61
     for
    0.59
     easy
    0.58
    な
    0.58
     and
    0.58
     low
    0.57
    いる
    0.57
    álló
    0.56
    Activations Density 0.947%

    No Known Activations