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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 1103
    Prev
    Next
    INDEX
    Explanations

    expressions of personal pronouns and subjective statements

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

    Follows a pronoun by an adverb

    np_acts-logits-general · gemini-2.0-flash

    personal opinion and consequence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     however
    -1.20
    however
    -1.10
     porém
    -0.92
    However
    -0.89
     echter
    -0.89
     jednak
    -0.88
     però
    -0.87
     imidlertid
    -0.84
     însă
    -0.82
     However
    -0.82
    POSITIVE LOGITS
     accordingly
    1.09
     consequently
    0.98
     correspondingly
    0.98
    何より
    0.97
     therefor
    0.81
     derfor
    0.80
     dermed
    0.79
     consequent
    0.78
     frankly
    0.78
     daarbij
    0.76
    Activations Density 0.527%

    No Known Activations