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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 8061
    Prev
    Next
    INDEX
    Explanations

    references to different types of formats, particularly in the context of media and publication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DeleteBehavior
    -0.64
     للاسماء
    -0.59
     actionMode
    -0.56
     MessageBoxIcon
    -0.56
    AddTagHelper
    -0.56
    новништво
    -0.55
     Administrativna
    -0.54
     desmotivaciones
    -0.54
    principalColumn
    -0.52
     dévelo
    -0.51
    POSITIVE LOGITS
     format
    1.06
     formats
    0.90
     Format
    0.90
     measuring
    0.87
    Format
    0.83
     Measuring
    0.79
     measurement
    0.76
     FORMAT
    0.75
     Formats
    0.75
    format
    0.74
    Activations Density 0.186%

    No Known Activations