© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 4821
    Prev
    Next
    INDEX
    Explanations

    expressions of deep contemplation or significant thoughts

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

    the word "thought" followed by a hyphen or other punctuation.

    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
    SharedDtor
    -0.71
     <>",
    -0.66
    الإنجليزية
    -0.59
    anyahu
    -0.57
    𑄮
    -0.56
    stateProvider
    -0.56
     NavController
    -0.56
     useParams
    -0.55
    <pad>
    -0.54
    antMatchers
    -0.54
    POSITIVE LOGITS
    Thought
    0.64
     Thought
    0.59
    thought
    0.56
    provoking
    0.54
     thought
    0.51
     THOUGHT
    0.49
     provoking
    0.46
     processes
    0.43
    ght
    0.40
     process
    0.39
    Activations Density 0.101%

    No Known Activations