© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 15071
    Prev
    Next
    INDEX
    Explanations

    detailed descriptions of physical attributes and features of items, particularly focusing on appearance and specifications

    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
    bootstrapcdn
    -0.52
     Pingback
    -0.51
    migrationBuilder
    -0.47
    httphttps
    -0.47
    didSet
    -0.46
     Sando
    -0.45
     MainAxisSize
    -0.45
    principalColumn
    -0.44
    AKAN
    -0.43
    tvguidetime
    -0.43
    POSITIVE LOGITS
    /*
    0.43
    دانشنامهٔ
    0.41
    іод
    0.40
     Verhältnisse
    0.40
    ⟬
    0.39
    omla
    0.38
    vraagd
    0.37
    AutoField
    0.36
     Umgang
    0.36
    CloseOperation
    0.36
    Activations Density 0.231%

    No Known Activations