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-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 10601
    Prev
    Next
    INDEX
    Explanations

    keywords related to business decisions and corporate actions

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

    future plans

    np_acts-logits-general · gemini-2.0-flash

    considering future actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     OFDb
    -0.63
     صوتيه
    -0.52
     apology
    -0.52
     [*]
    -0.50
     iniqu
    -0.49
    opa
    -0.49
    脚注の使い方
    -0.49
     acostumb
    -0.47
     Rine
    -0.47
    thodes
    -0.47
    POSITIVE LOGITS
     considering
    1.37
     consideration
    1.31
     contemplating
    1.23
     CONSIDER
    1.23
    considering
    1.17
     exploring
    1.15
     consider
    1.15
     Consideration
    1.13
     contemplate
    1.12
     explored
    1.11
    Activations Density 0.407%

    No Known Activations