© 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-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 10836
    Prev
    Next
    INDEX
    Explanations

    phrases indicating suggestion or possibility

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

    Followed by an action/suggestion

    np_acts-logits-general · gemini-2.0-flash

    modal verbs followed by action verbs

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     Infór
    -0.54
    /*
    -0.49
    attutto
    -0.46
     ressemb
    -0.45
    pecabe
    -0.45
    Portale
    -0.43
     cherchés
    -0.43
    ेमाल
    -0.41
     CommonModule
    -0.40
     niega
    -0.40
    POSITIVE LOGITS
     Administrativna
    0.58
     use
    0.51
     set
    0.49
    RefNanny
    0.47
     didst
    0.47
     actively
    0.47
     switch
    0.43
     слід
    0.42
     prepare
    0.42
     будешь
    0.42
    Activations Density 0.810%

    No Known Activations