© 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. 15-GEMMASCOPE-RES-16K
    6. 2187
    Prev
    Next
    INDEX
    Explanations

    elements of suspense and psychological intrigue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.48
     Infórmanos
    -0.43
    endpush
    -0.38
    #
    -0.38
    lindungan
    -0.37
    visející
    -0.37
     allá
    -0.37
    ElementType
    -0.37
    脚注の使い方
    -0.36
    Descricao
    -0.35
    POSITIVE LOGITS
    ChildScrollView
    0.60
     AssemblyCompany
    0.55
     mesmerizing
    0.53
     Wiktionnaire
    0.51
    verwijspagina
    0.50
     jScrollPane
    0.49
    AutoScaleMode
    0.48
    Feels
    0.47
     hypno
    0.45
    ruiter
    0.45
    Activations Density 0.324%

    No Known Activations