© 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. 2298
    Prev
    Next
    INDEX
    Explanations

    words related to additional requirements or conditions

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

    complex grammatical structures involving auxiliary verbs like "also", "would", "had", "need", and "can".

    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
    httphttps
    -0.61
     AssertionError
    -0.52
    styleType
    -0.52
    乓
    -0.47
    istert
    -0.44
    Atoi
    -0.44
     defaultstate
    -0.43
    windowFixed
    -0.42
    lunda
    -0.41
    äsent
    -0.41
    POSITIVE LOGITS
     simultaneously
    0.53
     além
    0.53
     additionally
    0.52
     concurrently
    0.52
     علاوه
    0.51
    simult
    0.49
     tillegg
    0.48
     besides
    0.47
     וגם
    0.46
    同時に
    0.46
    Activations Density 0.342%

    No Known Activations