© 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. 15532
    Prev
    Next
    INDEX
    Explanations

    information related to eligibility criteria and requirements for participation in studies or programs

    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
     la
    -0.24
    取
    -0.22
     “
    -0.22
    “
    -0.22
    こ
    -0.21
     forhold
    -0.21
     por
    -0.21
     text
    -0.21
    zi
    -0.21
     }
    -0.21
    POSITIVE LOGITS
     EconPapers
    1.18
     autorytatywna
    1.00
     Numerade
    0.94
    Personendaten
    0.94
    InputBorder
    0.93
     InputDecoration
    0.92
    ReusableCell
    0.92
    tvguidetime
    0.91
    SourceChecksum
    0.91
    ロウィン
    0.89
    Activations Density 0.340%

    No Known Activations