© 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. 2268
    Prev
    Next
    INDEX
    Explanations

    concepts related to cultural identity and pride

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

    phrases about national or political identity, particularly related to place names and symbolic meanings.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    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
     sneaky
    -0.59
     Normdatei
    -0.56
     newbies
    -0.53
     weirdly
    -0.52
     documentaire
    -0.50
    Билгалдахарш
    -0.50
     amuse
    -0.49
     surla
    -0.49
     trolls
    -0.47
    umably
    -0.47
    POSITIVE LOGITS
     unſ
    0.39
     impegno
    0.38
     responsabilità
    0.38
     compromisso
    0.36
     today
    0.36
     commitment
    0.36
     amortecedor
    0.36
     Asamblea
    0.35
     doInBackground
    0.35
    我们是
    0.35
    Activations Density 0.134%

    No Known Activations