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. 25-GEMMASCOPE-RES-16K
    6. 12559
    Prev
    Next
    INDEX
    Explanations

    terms related to personal development and guidance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 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
    adaptiveStyles
    -0.69
    WithIOException
    -0.65
     متعلقه
    -0.57
    Hochspringen
    -0.57
     تضيفلها
    -0.53
    原始内容存档于
    -0.53
    SequentialGroup
    -0.53
    HttpFoundation
    -0.52
     JpaRepository
    -0.52
     ligiloj
    -0.51
    POSITIVE LOGITS
     speaker
    0.78
     motivational
    0.75
     author
    0.74
     bestselling
    0.70
     Speaker
    0.65
     confé
    0.65
     motiv
    0.63
     Motiv
    0.63
    Speaker
    0.62
    Author
    0.61
    Activations Density 0.236%

    No Known Activations