© 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. 2421
    Prev
    Next
    INDEX
    Explanations

    phrases related to educational assessments and feedback

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

    verbs describing action or participation, particularly around learning, completing tasks, or taking opportunities.

    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
     chemistry
    -0.36
    <?
    -0.35
     contener
    -0.34
    httphttps
    -0.34
    XmlAccessorType
    -0.32
    ίδι
    -0.32
    GenerationType
    -0.32
     legacy
    -0.30
     my
    -0.30
     Flasche
    -0.29
    POSITIVE LOGITS
     themselves
    0.94
    themselves
    0.80
     ihre
    0.71
     their
    0.67
     jspb
    0.65
     själva
    0.65
    Their
    0.63
     ſind
    0.62
     kanilang
    0.62
    their
    0.62
    Activations Density 0.802%

    No Known Activations