© 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. 18-GEMMASCOPE-RES-16K
    11. 914
    Prev
    Next
    INDEX
    Explanations

    numeric values often associated with coding or technical specifications

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

    Numbers following "1-800-" or similar prefixes

    np_acts-logits-general · gemini-2.0-flash

    numbers following two

    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
     FormGroup
    -0.58
     esp
    -0.55
     qu
    -0.53
     '{@
    -0.53
     sa
    -0.53
    ياء
    -0.53
     kirj
    -0.52
    :///
    -0.52
     O
    -0.52
     R
    -0.51
    POSITIVE LOGITS
     myſelf
    1.18
     Efq
    1.11
     pleaſure
    1.10
     ſche
    1.08
     itſelf
    1.06
     raiſ
    1.02
     chofe
    1.01
     Monfieur
    1.00
     Diſ
    0.99
     faſt
    0.99
    Activations Density 0.482%

    No Known Activations