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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 1050
    Prev
    Next
    INDEX
    Explanations

    expressions of personal experiences and feelings

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

    Preceding certain verbs or adjectives

    np_acts-logits-general · gemini-2.0-flash

    prepositional phrases and clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.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
    GEBURTSDATUM
    -0.68
    uxxxx
    -0.67
    DockStyle
    -0.63
     NSCoder
    -0.63
     houſe
    -0.61
     ſtate
    -0.57
     Houſe
    -0.57
    lovakia
    -0.56
    ſelf
    -0.54
     disambiguazione
    -0.54
    POSITIVE LOGITS
     wikipagina
    0.43
     vermeld
    0.41
    being
    0.40
    OVERR
    0.40
     vermogen
    0.39
     voeten
    0.39
    addGap
    0.39
     groote
    0.39
     bouwen
    0.38
     redenen
    0.38
    Activations Density 0.861%

    No Known Activations