© 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. 18-GEMMASCOPE-RES-16K
    6. 9645
    Prev
    Next
    INDEX
    Explanations

    the word "or" in various contexts

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

    "or" followed by alternatives

    np_acts-logits-general · gemini-2.0-flash

    or

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -1.10
     Majefty
    -1.08
     Shakspeare
    -1.06
     ―――――
    -1.03
     Jefus
    -1.02
     Houſe
    -1.01
     Chriftian
    -0.98
     himſelf
    -0.97
     Reſ
    -0.97
     themſelves
    -0.97
    POSITIVE LOGITS
     even
    1.23
     else
    1.13
     otherwise
    1.01
     perhaps
    0.96
     any
    0.96
     simply
    0.95
     other
    0.93
     bahkan
    0.92
    otherwise
    0.84
     something
    0.84
    Activations Density 0.244%

    No Known Activations