© 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. 14152
    Prev
    Next
    INDEX
    Explanations

    themes related to personal identity and human relationships

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

    possessive pronouns paired with abstract or human-centered nouns (particularly "our," "their," "her," "his," "my," "s'" followed by words related to identity, nature, body, capacity, health, humanity, and similar concepts).

    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
    httphttps
    -0.48
     thing
    -0.47
     traveler
    -0.46
     dude
    -0.46
    nthesis
    -0.45
     dreamer
    -0.45
     BoxFit
    -0.45
    Comun
    -0.44
     paparazzi
    -0.44
     superstition
    -0.44
    POSITIVE LOGITS
     own
    0.67
     ability
    0.52
    windowFixed
    0.51
     OSError
    0.46
     referrerpolicy
    0.46
     activities
    0.45
     (_,
    0.42
     Activities
    0.42
     persoonlijke
    0.41
     inability
    0.41
    Activations Density 0.637%

    No Known Activations