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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 15588
    Prev
    Next
    INDEX
    Explanations

    the frequency of the word "the" and variations of "his" or "this" within different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_25/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.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Hozzáférés
    -0.68
    原始内容存档于
    -0.54
    Personendaten
    -0.49
    findpost
    -0.46
    原始内容存档
    -0.44
    initWithFrame
    -0.40
    ểm
    -0.39
     оригіналу
    -0.39
    EndContext
    -0.38
    addComponent
    -0.37
    POSITIVE LOGITS
    +#+
    0.45
     jadx
    0.45
     fédéral
    0.44
    RTEE
    0.43
    SharedCtor
    0.43
    Handlung
    0.42
     yoksa
    0.42
    oredCriteria
    0.41
    хьтан
    0.40
    +#+#
    0.40
    Activations Density 0.605%

    No Known Activations