© 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. 570
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "which" and its variants throughout the text

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

    Code snippets or mathematical expressions ending with })

    np_acts-logits-general · gemini-2.0-flash

    followed by relative clauses

    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
    rungsseite
    -0.71
     Houſe
    -0.55
    Aiheesta
    -0.54
    DockStyle
    -0.49
    elemField
    -0.48
     itſelf
    -0.47
     houſe
    -0.45
    cookieParser
    -0.45
     nakalista
    -0.44
     Verſ
    -0.44
    POSITIVE LOGITS
     nicest
    0.49
    Spoljašnje
    0.49
     I
    0.49
     ***!
    0.49
     my
    0.45
     grieve
    0.44
    mel
    0.43
    Never
    0.42
    +#+
    0.42
    rayal
    0.42
    Activations Density 0.868%

    No Known Activations