© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 12256
    Prev
    Next
    INDEX
    Explanations

    terms related to "conflict" and "confounding" in various contexts

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

    "conf" (or variations)

    np_acts-logits-general · gemini-2.0-flash

    words starting with "conf"

    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
     noDo
    -0.57
    MessageOf
    -0.54
    +#+#
    -0.53
    KommentareTeilen
    -0.53
     Diogo
    -0.53
    cheme
    -0.52
    enterOuterAlt
    -0.51
    lads
    -0.51
    dall
    -0.50
    วัส
    -0.49
    POSITIVE LOGITS
     Conf
    0.77
     CONF
    0.76
    conf
    0.67
    Conf
    0.67
     Konf
    0.66
     conf
    0.63
    řízení
    0.62
    ratulations
    0.60
    CONF
    0.60
     Numerology
    0.60
    Activations Density 0.100%

    No Known Activations