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
    4. Residual Stream - 131k
    5. 24-GEMMASCOPE-RES-131K
    6. 1169
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names, especially in historical or geographical contexts

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

    place names and suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mijne
    -0.47
     wikipagina
    -0.41
     zijne
    -0.38
     schoenen
    -0.37
     flyknit
    -0.37
     Normdatei
    -0.36
    räck
    -0.36
     rallado
    -0.36
     spørgsmål
    -0.36
     erfaring
    -0.35
    POSITIVE LOGITS
     Italijani
    0.58
    hythm
    0.52
    uxxxx
    0.49
     مرئيه
    0.48
     tph
    0.47
     wireType
    0.46
     Di
    0.45
     Kl
    0.45
     Mf
    0.44
     Dutch
    0.44
    Activations Density 0.025%

    No Known Activations