© 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. 8383
    Prev
    Next
    INDEX
    Explanations

    discussions about personal experiences and opinions related to feelings and subjective situations

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

    personal pronouns and possessive adjectives that indicate relationships between individuals.

    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
     المعيارى
    -0.66
    ArrowToggle
    -0.66
     Audiodateien
    -0.57
    libft
    -0.56
     Normdatei
    -0.56
    Cyfarwyddwr
    -0.56
    SourceChecksum
    -0.56
     lenker
    -0.55
    +#+
    -0.54
    ()");
    -0.53
    POSITIVE LOGITS
     ours
    3.00
     yours
    2.69
     mine
    2.67
     hers
    2.52
     theirs
    2.48
     Ours
    2.33
    Ours
    2.27
    Mine
    2.19
     Mine
    2.08
     Yours
    2.05
    Activations Density 0.505%

    No Known Activations