Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 5715
    Prev
    Next
    INDEX
    Explanations

    phrases related to making decisions and seeking solutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Бахар
    -0.42
     known
    -0.40
    Notae
    -0.40
    uan
    -0.39
    known
    -0.36
    Known
    -0.36
     Known
    -0.35
    ыгана
    -0.33
     извест
    -0.33
     conhecido
    -0.33
    POSITIVE LOGITS
     suitable
    0.56
     appropriate
    0.56
     appropriateness
    0.54
     optimum
    0.52
    适合
    0.52
     suited
    0.51
    suitable
    0.50
    合适
    0.49
    󠁢
    0.49
     suits
    0.49
    Activations Density 0.256%

    No Known Activations