© 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. 4818
    Prev
    Next
    INDEX
    Explanations

    references to deception or manipulation

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

    the phrase "make [a/the] [noun]" where the noun represents something foolish, absurd, or negatively characterized.

    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
    PerformLayout
    -0.65
    WireFormatLite
    -0.58
    MemoryWarning
    -0.54
    hared
    -0.51
    éal
    -0.51
    "]);
    -0.50
    enumii
    -0.50
     HttpNotFound
    -0.50
    quels
    -0.49
     ſta
    -0.49
    POSITIVE LOGITS
     daraus
    0.56
     make
    0.41
    make
    0.37
     Make
    0.36
     out
    0.35
     получилось
    0.33
     tästä
    0.32
     Roskov
    0.32
    Make
    0.32
    fromCharCode
    0.32
    Activations Density 0.215%

    No Known Activations