© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 16020
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to instructions or requests

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

    the infinitive form "to" followed by action verbs in imperative or instructional contexts.

    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
     Fazit
    -0.43
     الرياضيه
    -0.43
     löytyy
    -0.36
     zależy
    -0.36
     laikā
    -0.35
     للاسماء
    -0.34
     nød
    -0.34
    ใคร
    -0.34
     للمعارف
    -0.34
     condena
    -0.34
    POSITIVE LOGITS
     möge
    0.70
     come
    0.67
     please
    0.59
     reconsider
    0.56
     become
    0.56
    makeConstraints
    0.56
     rethink
    0.54
    Come
    0.54
     переста
    0.54
     Come
    0.53
    Activations Density 0.297%

    No Known Activations