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. 5801
    Prev
    Next
    INDEX
    Explanations

    references to various statistical distributions and tests

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

    Tests related to statistical distributions or stats

    np_acts-logits-general · gemini-2.0-flash

    mathematical distributions and statistics

    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
     eig
    -0.45
    createQuery
    -0.45
     parecido
    -0.45
     slå
    -0.43
    ParallelGroup
    -0.43
     quadrangle
    -0.42
     chì
    -0.42
     ".";
    -0.41
     Galo
    -0.40
    eraard
    -0.39
    POSITIVE LOGITS
    +#+#
    0.98
    +#+
    0.96
    GEBURTSDATUM
    0.89
    AddTagHelper
    0.84
    +:+
    0.84
     صوتيه
    0.83
    #+#
    0.70
     المعيارى
    0.70
    tagHelperRunner
    0.65
    DockStyle
    0.63
    Activations Density 0.253%

    No Known Activations