© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 4669
    Prev
    Next
    INDEX
    Explanations

    expressions of identity and personal experience

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

    Explanation of neuron 4 behavior: the main thing this neuron does is find conversational exchanges involving direct speech and dialogue between people.

    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
     करती
    -0.59
    лтамалар
    -0.49
     &___
    -0.47
    heh
    -0.44
    她們
    -0.42
    reportWebVitals
    -0.42
    megen
    -0.41
     acompañada
    -0.41
    stateParams
    -0.40
    Попис
    -0.40
    POSITIVE LOGITS
     he
    3.13
     his
    2.75
     him
    2.63
    彼は
    2.52
     그는
    2.39
    彼が
    2.33
     egli
    2.25
    彼の
    2.16
     그의
    2.09
    his
    2.08
    Activations Density 3.498%

    No Known Activations