© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 15379
    Prev
    Next
    INDEX
    Explanations

    references to a specific type of book or publication, particularly those related to personal experiences and mental health

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     TextAppearance
    -0.65
     Gardner
    -0.62
     gard
    -0.58
     estimés
    -0.55
    Gardner
    -0.55
     Enix
    -0.55
    Plural
    -0.53
     snippetHide
    -0.52
     Parenthood
    -0.51
     jornadas
    -0.51
    POSITIVE LOGITS
    thrift
    0.95
    Thrift
    0.92
    iprot
    0.91
     iprot
    0.84
    StructEnd
    0.81
     TType
    0.80
     thrift
    0.79
     Thrift
    0.78
    oprot
    0.67
    TProtocol
    0.66
    Activations Density 0.184%

    No Known Activations