© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 4329
    Prev
    Next
    INDEX
    Explanations

    scientific terminology related to control variables and conditions in experiments

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

    "control" or "actin"

    np_acts-logits-general · gemini-2.0-flash

    control and actin

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Autorizaciones
    -0.69
     الحره
    -0.68
    AddTagHelper
    -0.60
     propOrder
    -0.59
     StringTokenizer
    -0.57
    enumii
    -0.56
    AddHtmlAttribute
    -0.55
     GenerationType
    -0.55
     CreateTagHelper
    -0.55
     &___
    -0.55
    POSITIVE LOGITS
     piese
    0.38
     oczywiście
    0.37
    もちろん
    0.36
     pemer
    0.36
     évidemment
    0.35
     itself
    0.35
    ONAUT
    0.35
     cuire
    0.35
     Lengkap
    0.34
    FromNib
    0.34
    Activations Density 0.880%

    No Known Activations