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. 24-GEMMASCOPE-RES-16K
    6. 16335
    Prev
    Next
    INDEX
    Explanations

    terms related to particle methods in statistical inference

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    probability distributions or Bayesian statistics

    np_acts-logits-general · gemini-2.0-flash

    Bayesian inference and estimation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aarrggbb
    -0.79
     متعلقه
    -0.75
     defaultstate
    -0.68
    +#+#
    -0.64
    __(/*!
    -0.60
    providedIn
    -0.59
    createStatement
    -0.58
    TProtocol
    -0.56
    SourceChecksum
    -0.56
     useAppContext
    -0.55
    POSITIVE LOGITS
     posterior
    1.03
     prior
    0.98
    prior
    0.93
    Prior
    0.90
     priors
    0.89
     Posterior
    0.88
    posterior
    0.85
     likelihood
    0.85
     Prior
    0.85
    Posterior
    0.80
    Activations Density 1.406%

    No Known Activations