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. 13655
    Prev
    Next
    INDEX
    Explanations

    references and citations in academic papers

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

    "pp" followed by a period or number

    np_acts-logits-general · gemini-2.0-flash

    pages in academic citations

    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
    OGND
    -0.76
     typelib
    -0.68
    +#+#
    -0.65
    InitVars
    -0.65
    AccessorTable
    -0.58
    <?=$
    -0.55
    ()];
    -0.54
     Bon
    -0.53
    bootstrapcdn
    -0.53
    unknownFields
    -0.53
    POSITIVE LOGITS
     Ceux
    0.60
     féminine
    0.57
     Allí
    0.52
    Mutagenicity
    0.52
     quæ
    0.50
    CrossRef
    0.49
     Celui
    0.49
     Suivez
    0.49
     câte
    0.49
     Muchos
    0.49
    Activations Density 0.342%

    No Known Activations