© 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. 20-GEMMASCOPE-RES-16K
    6. 11901
    Prev
    Next
    INDEX
    Explanations

    comparisons and contrasts between subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
     zde
    -0.37
     consultato
    -0.35
     člá
    -0.35
     náš
    -0.34
     beliau
    -0.34
     noastre
    -0.33
     CreateTagHelper
    -0.32
    发表于
    -0.32
    Soorten
    -0.32
     etc
    -0.31
    POSITIVE LOGITS
     invokingState
    0.57
     TestBed
    0.56
    RTEX
    0.54
    UserScript
    0.50
    SourceChecksum
    0.49
    localctx
    0.48
    edance
    0.46
     Whig
    0.46
     improvis
    0.46
    ussian
    0.45
    Activations Density 0.274%

    No Known Activations