© 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. 8868
    Prev
    Next
    INDEX
    Explanations

    references to artificial or fake concepts and entities

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

    the word "fake" and related concepts of artificiality or inauthenticity.

    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
    -0.48
     šķ
    -0.43
     Energ
    -0.38
     automáticamente
    -0.38
    entlich
    -0.36
    anyeol
    -0.36
     espac
    -0.36
    uário
    -0.36
     före
    -0.35
    pēc
    -0.35
    POSITIVE LOGITS
     IBOutlet
    0.59
     Faker
    0.57
     Fake
    0.56
     pretending
    0.55
     pretend
    0.54
    pushFollow
    0.54
    BufferException
    0.54
     fake
    0.53
     pretends
    0.53
    LookAnd
    0.52
    Activations Density 0.395%

    No Known Activations