© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 6804
    Prev
    Next
    INDEX
    Explanations

    concepts related to risks and influencing factors in various contexts

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

    Follows nouns modified by "such as"

    np_acts-logits-general · gemini-2.0-flash

    introducing examples with such as

    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
     kasarigan
    -0.68
     ""],
    -0.66
     незавершена
    -0.63
    genicity
    -0.58
    '])->
    -0.58
    <_>
    -0.57
    Referencies
    -0.56
    __":
    -0.56
    inafter
    -0.56
    KURZBESCHREIBUNG
    -0.55
    POSITIVE LOGITS
     such
    3.62
    such
    2.96
     like
    2.76
     SUCH
    2.42
    Such
    2.38
     Such
    2.31
     telles
    2.18
     takich
    2.15
     såsom
    2.12
     seperti
    2.12
    Activations Density 2.237%

    No Known Activations