© 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-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 16912
    Prev
    Next
    INDEX
    Explanations

    negations or phrases indicating that something is not required or necessary

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

    not required action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    matchCondition
    -0.59
    StructEnd
    -0.59
     للمعارف
    -0.56
    ########.
    -0.52
     resurre
    -0.51
     agre
    -0.49
     comesti
    -0.48
     magasiner
    -0.48
     converti
    -0.47
    pgterms
    -0.47
    POSITIVE LOGITS
    <bos>
    0.49
     Pierson
    0.43
     Pingback
    0.41
    eraard
    0.41
    延伸閱讀
    0.40
    还得
    0.40
    jalá
    0.40
     tevens
    0.40
     liever
    0.40
    即便
    0.39
    Activations Density 0.007%

    No Known Activations