© 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-2-9B
    7. Residual Stream - 131k
    9. 24-GEMMASCOPE-RES-131K
    11. 208
    Prev
    Next
    INDEX
    Explanations

    the preposition "For" indicating purpose or reason

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

    for example

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    購入した
    -0.40
    󠁴
    -0.40
    ruik
    -0.36
     Baumann
    -0.36
     iVar
    -0.36
     MSA
    -0.35
     Ensuite
    -0.35
     avance
    -0.35
    ExtendWith
    -0.35
    //~
    -0.35
    POSITIVE LOGITS
     For
    0.57
    For
    0.57
     للمعارف
    0.56
     example
    0.52
    ForValue
    0.51
     instance
    0.50
    Για
    0.49
     FOR
    0.49
    FOR
    0.49
     autorytatywna
    0.48
    Activations Density 0.099%

    No Known Activations