© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 2972
    Prev
    Next
    INDEX
    Explanations

    references to benefits in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    دانشنامهٔ
    -0.50
     $_"
    -0.48
     femininas
    -0.47
     nahilalakip
    -0.47
     russes
    -0.46
     roleId
    -0.46
     Russians
    -0.46
     xrange
    -0.45
    arache
    -0.45
    Clik
    -0.44
    POSITIVE LOGITS
     benefit
    0.75
    benefit
    0.66
    Benefit
    0.65
     BENE
    0.65
     Benefit
    0.64
     BENEFITS
    0.63
     ticket
    0.62
     benefits
    0.60
     todo
    0.59
     tickets
    0.59
    Activations Density 0.194%

    No Known Activations