© 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. 8810
    Prev
    Next
    INDEX
    Explanations

    text related to organizational structures and roles within societal contexts

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

    structural or organizational transitions and formal changes in status or composition.

    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
     plain
    -0.45
     неза
    -0.40
    Plain
    -0.40
    raw
    -0.37
    plain
    -0.35
     NON
    -0.35
     sederhana
    -0.35
    grund
    -0.35
    PLAIN
    -0.35
     simpl
    -0.34
    POSITIVE LOGITS
     formal
    1.33
    Formal
    1.20
     formalized
    1.18
    formal
    1.16
     Formal
    1.13
     formally
    1.09
     formales
    0.98
    正式
    0.93
     organised
    0.87
     formality
    0.86
    Activations Density 0.993%

    No Known Activations