© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 5114
    Prev
    Next
    INDEX
    Explanations

    elements related to processes, actions, and their outcomes within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Geographie
    -0.53
     للاسماء
    -0.53
     mijne
    -0.52
    deelte
    -0.51
     meille
    -0.51
    moveToFirst
    -0.50
     disambiguazione
    -0.50
    เอง
    -0.50
    ımız
    -0.50
     Meksiku
    -0.49
    POSITIVE LOGITS
     its
    3.13
    Its
    2.17
     Its
    2.11
    its
    1.92
    它的
    1.85
    其
    1.82
     její
    1.70
     jej
    1.59
     її
    1.59
     dessen
    1.57
    Activations Density 1.969%

    No Known Activations