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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 3959
    Prev
    Next
    INDEX
    Explanations

    terms associated with the concept of retention and its impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     $(".
    -0.35
    $(".
    -0.33
    いただいた
    -0.31
     tub
    -0.31
    addGroup
    -0.30
     glasses
    -0.30
     feature
    -0.30
     tin
    -0.30
     less
    -0.30
     discouraged
    -0.29
    POSITIVE LOGITS
     retention
    0.87
     Retention
    0.84
    retention
    0.82
     reten
    0.74
    verwijspagina
    0.74
     Scenarios
    0.72
     automation
    0.71
    Retention
    0.71
     scenario
    0.70
     scenarios
    0.69
    Activations Density 0.131%

    No Known Activations