Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 16290
    Prev
    Next
    INDEX
    Explanations

    instances of being compelled or forced to act under various circumstances

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

    "Forced" or "compelled" followed by "to"

    np_acts-logits-general · gemini-2.0-flash

    forced to VERB

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    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
     ModelExpression
    -0.65
     kasarigan
    -0.60
    Personendaten
    -0.48
     مشين
    -0.45
    ########.
    -0.42
    NameInMap
    -0.40
    BagConstraints
    -0.40
    consulté
    -0.40
     doInBackground
    -0.39
    ISupport
    -0.38
    POSITIVE LOGITS
     forced
    1.93
     terpaksa
    1.83
    forced
    1.70
     выну
    1.66
     Forced
    1.66
    Forced
    1.63
    不得不
    1.46
    被迫
    1.42
     gezwungen
    1.38
     пришлось
    1.37
    Activations Density 0.427%

    No Known Activations