© 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. 35-GEMMASCOPE-RES-16K
    6. 6853
    Prev
    Next
    INDEX
    Explanations

    references to times or temporal transitions in the narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __":
    -0.59
    __":
    
    -0.56
    iettivo
    -0.53
     <=",
    -0.53
     <>",
    -0.52
    ActionCreators
    -0.52
     previous
    -0.51
     propOrder
    -0.50
    setupUi
    -0.48
     early
    -0.47
    POSITIVE LOGITS
     Verlauf
    0.49
     than
    0.46
     فريبيس
    0.44
     versioni
    0.44
     versiones
    0.43
     versões
    0.40
    als
    0.40
     versions
    0.39
    shadowRadius
    0.39
     Hoje
    0.37
    Activations Density 0.098%

    No Known Activations