© 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. 40-GEMMASCOPE-RES-16K
    6. 5459
    Prev
    Next
    INDEX
    Explanations

    the phrase "one" in various contexts, particularly with numeric or comparative associations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.62
     <<<<<<<<<<<<<<
    -0.47
    libft
    -0.46
    Identyfik
    -0.46
     незавершена
    -0.45
     autorytatywna
    -0.43
    xase
    -0.42
    الإنجليزية
    -0.41
    titleMargin
    -0.41
     للاسماء
    -0.40
    POSITIVE LOGITS
    shots
    0.63
     shots
    0.61
    shot
    0.60
     shot
    0.56
    Shots
    0.55
     Shot
    0.54
    Shot
    0.53
    sided
    0.53
     touch
    0.52
     Shots
    0.51
    Activations Density 0.185%

    No Known Activations