© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 34-GEMMASCOPE-RES-16K
    6. 11395
    Prev
    Next
    INDEX
    Explanations

    phrases related to stages and phases in processes or events

    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
    новниш
    -0.51
    Personensuche
    -0.44
    scribe
    -0.43
    strix
    -0.42
    OCCURRED
    -0.42
    WebElementEntity
    -0.42
    thenes
    -0.41
    OGND
    -0.41
     arşivlendi
    -0.40
    BagLayout
    -0.40
    POSITIVE LOGITS
     stage
    3.25
     stages
    2.91
     Stage
    2.73
     phase
    2.73
    stage
    2.66
    Stage
    2.63
     STAGE
    2.58
    stages
    2.41
     Stages
    2.41
     phases
    2.36
    Activations Density 1.057%

    No Known Activations