© 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. 6233
    Prev
    Next
    INDEX
    Explanations

    instructions related to API usage and data manipulation in programming

    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
     Monfieur
    -1.25
     Theſe
    -1.21
     Anſ
    -1.17
     Egli
    -1.17
     Efq
    -1.15
     Reſ
    -1.12
     Cæsar
    -1.12
     Diſ
    -1.09
     Houſe
    -1.08
     Diretto
    -1.04
    POSITIVE LOGITS
     que
    0.65
     e
    0.64
     dos
    0.61
     de
    0.60
     ou
    0.60
     por
    0.59
     das
    0.59
     da
    0.57
     em
    0.56
     mais
    0.55
    Activations Density 0.113%

    No Known Activations