© 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-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 9198
    Prev
    Next
    INDEX
    Explanations

    information related to the costs and expenses associated with events or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     skall
    -0.67
    szönöm
    -0.63
    Thankyou
    -0.61
     Description
    -0.61
    NamedQueries
    -0.56
     تشکر
    -0.55
    Description
    -0.54
     iż
    -0.54
     Complimentary
    -0.52
     menciona
    -0.52
    POSITIVE LOGITS
    +#+#
    0.64
     editors
    0.60
    !*\
    0.59
     lenker
    0.58
    Skocz
    0.58
     roundup
    0.57
    Tarih
    0.57
     picks
    0.57
    tested
    0.56
     reader
    0.56
    Activations Density 0.192%

    No Known Activations