© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 11428
    Prev
    Next
    INDEX
    Explanations

    concepts related to research methodologies and the ethical implications of consent

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

    Statements of inadequacy or insufficiency

    np_acts-logits-general · gemini-2.0-flash

    insufficient or flawed

    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
    BagConstraints
    -0.55
    没事
    -0.55
    انيف
    -0.53
     Happen
    -0.53
    strix
    -0.52
     Wiktionnaire
    -0.51
    ModelMap
    -0.51
    ousand
    -0.50
    pecha
    -0.50
     محفوظة
    -0.49
    POSITIVE LOGITS
     lacks
    1.35
     fails
    1.31
     inadequ
    1.21
     insufficient
    1.18
     lacked
    1.18
     inadequate
    1.16
     fail
    1.10
     lack
    1.09
     poorly
    1.03
     misses
    1.03
    Activations Density 0.969%

    No Known Activations