© 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-2-9B
    7. Residual Stream - 16k
    9. 27-GEMMASCOPE-RES-16K
    11. 11556
    Prev
    Next
    INDEX
    Explanations

    themes related to expectations and the pressures involved in meeting them

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ientras
    -0.47
     مشين
    -0.45
     ujednoznacz
    -0.44
    COPYRIGHT
    -0.42
     disambiguazione
    -0.41
    Legături
    -0.39
    NOPQRST
    -0.39
    为止
    -0.38
    曖昧さ回避
    -0.38
     StringTokenizer
    -0.37
    POSITIVE LOGITS
     pressure
    1.35
    Pressure
    1.23
     Pressure
    1.20
     PRESSURE
    1.12
    pressure
    1.10
     pressures
    1.02
    压力
    0.98
     expectations
    0.97
     pressured
    0.90
     presión
    0.90
    Activations Density 0.204%

    No Known Activations