© 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-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 11010
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "off" in various contexts

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

    hyphenated words or phrases beginning with "off" (such as "off-the-wall," "off-kilter," "off-label," "off-script").

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    KURZBESCHREIBUNG
    -0.51
     Италијани
    -0.45
    er
    -0.43
     tuin
    -0.42
     terecht
    -0.42
    Сюжет
    -0.41
    舞い
    -0.41
     voordeel
    -0.41
     betrekking
    -0.40
    =$?
    -0.40
    POSITIVE LOGITS
     Off
    1.15
    Off
    1.13
     off
    1.10
    off
    0.99
     OFF
    0.93
    OFF
    0.82
    オフ
    0.79
     offs
    0.76
     オフ
    0.69
    offs
    0.65
    Activations Density 0.086%

    No Known Activations