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. 3-GEMMASCOPE-RES-16K
    6. 6091
    Prev
    Next
    INDEX
    Explanations

    references to independence in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OGND
    -0.82
     Roskov
    -0.81
    ContentAlignment
    -0.72
    expandindo
    -0.68
    dagog
    -0.65
    примеча
    -0.63
    ❦
    -0.63
    WHEREAS
    -0.63
    reactor
    -0.63
     RequestMethod
    -0.62
    POSITIVE LOGITS
     independent
    3.57
     Independent
    3.43
    Independent
    3.35
    independent
    3.23
     INDEPENDENT
    2.98
     independ
    2.77
     independently
    2.65
     independence
    2.60
     Independ
    2.57
     Indep
    2.56
    Activations Density 0.073%

    No Known Activations