© 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. 16-GEMMASCOPE-RES-16K
    11. 8789
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a focus on specific actions or attributes

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

    "a" followed by uncommon words

    np_acts-logits-general · gemini-2.0-flash

    a followed by specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    襪
    -0.49
     troca
    -0.49
    нес
    -0.48
     Able
    -0.48
     No
    -0.47
    kadi
    -0.46
    ให
    -0.45
     Eins
    -0.45
     Kan
    -0.45
    No
    -0.44
    POSITIVE LOGITS
    tagHelperRunner
    1.08
    ViewFeatures
    0.94
    tableFuture
    0.86
     AssemblyCulture
    0.85
    noinspection
    0.82
    Abit
    0.78
     itſelf
    0.76
    OOTDTY
    0.75
    tvguidetime
    0.75
     ContentValues
    0.74
    Activations Density 0.134%

    No Known Activations