© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 15888
    Prev
    Next
    INDEX
    Explanations

    instructions and actions related to document management and printing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the word "right" used as a directional or positional indicator.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    omme
    -0.36
    NotBlank
    -0.36
    risi
    -0.36
    apimachinery
    -0.35
     Around
    -0.35
     wegen
    -0.35
    isDefault
    -0.35
    InitStructure
    -0.35
    notEmpty
    -0.34
     "<?
    -0.34
    POSITIVE LOGITS
     directly
    2.27
    directly
    2.11
     Directly
    2.00
     directamente
    1.98
     directement
    1.98
     direttamente
    1.95
     diretamente
    1.81
    直接
    1.74
     přímo
    1.71
     bezpośrednio
    1.71
    Activations Density 0.689%

    No Known Activations