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. 22-GEMMASCOPE-RES-16K
    6. 12605
    Prev
    Next
    INDEX
    Explanations

    concepts related to statistical estimation methods and inference

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

    Inference with latent variable models

    np_acts-logits-general · gemini-2.0-flash

    Bayesian inference, probability, and distributions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    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
    -0.76
     متعلقه
    -0.58
     specchio
    -0.52
    WindowConstants
    -0.51
     IndexPath
    -0.49
    grpc
    -0.48
    ClientSize
    -0.47
     Défense
    -0.47
    AVL
    -0.47
    ouro
    -0.47
    POSITIVE LOGITS
     priors
    1.00
     posterior
    0.97
     prior
    0.96
    Prior
    0.92
    prior
    0.88
     Prior
    0.86
     Posterior
    0.84
     Bayesian
    0.82
     likelihood
    0.82
    PRIOR
    0.82
    Activations Density 1.662%

    No Known Activations