© 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. 17-GEMMASCOPE-RES-16K
    6. 6177
    Prev
    Next
    INDEX
    Explanations

    references to significant events or conditions in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    حياته
    -0.63
    حياتها
    -0.61
     resourceCulture
    -0.55
    Архівовано
    -0.55
    __',
    -0.51
    DebuggerNonUser
    -0.49
    Kini
    -0.49
     certificación
    -0.48
    PREFERRED
    -0.48
    likely
    -0.47
    POSITIVE LOGITS
     wondering
    0.64
    COUVER
    0.63
    หวัด
    0.62
     there
    0.61
     lucky
    0.59
     worried
    0.59
    eria
    0.58
     fortunate
    0.58
    TagMode
    0.58
     surprised
    0.57
    Activations Density 0.087%

    No Known Activations