© 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. 23-GEMMASCOPE-RES-16K
    11. 14548
    Prev
    Next
    INDEX
    Explanations

    references to plans, strategies, or project names

    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
    enumi
    -0.53
    sopp
    -0.49
    spartner
    -0.48
    Portale
    -0.47
    ndes
    -0.46
    ClCompile
    -0.44
    adpleegd
    -0.44
     ^=
    -0.44
    onton
    -0.42
     Hilary
    -0.42
    POSITIVE LOGITS
    ets
    1.18
    eting
    1.07
    et
    1.01
    ETS
    0.96
    ET
    0.96
    ეტ
    0.95
    etting
    0.88
    etan
    0.86
    etto
    0.86
    etin
    0.85
    Activations Density 0.477%

    No Known Activations