© 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. 28-GEMMASCOPE-RES-16K
    6. 7589
    Prev
    Next
    INDEX
    Explanations

    terms related to dynamic systems and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Accounting for a phenomenon or effect

    np_acts-logits-general · gemini-2.0-flash

    accounts for or ignores effects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ScopeManager
    -0.55
    出版年
    -0.54
    EndContext
    -0.50
     пъ
    -0.45
     initWithFrame
    -0.44
     Италијани
    -0.43
     IndexPath
    -0.41
     badge
    -0.40
    isContained
    -0.40
     IBOutlet
    -0.39
    POSITIVE LOGITS
     effects
    0.75
     imperfections
    0.65
     interactions
    0.65
     effets
    0.65
    effects
    0.63
     EFFECTS
    0.63
     losses
    0.61
    Effects
    0.59
     Störungen
    0.58
     interaction
    0.57
    Activations Density 1.826%

    No Known Activations