© 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. 3934
    Prev
    Next
    INDEX
    Explanations

    technical terms and references related to chemical analysis and legal contexts

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

    Characters that sometimes represent non-English letters

    np_acts-logits-general · gemini-2.0-flash

    metal layer

    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
     AssemblyCulture
    -1.30
     nahilalakip
    -1.22
    IUrlHelper
    -1.13
    Lähteet
    -1.10
    存于互联网档案馆
    -1.09
    GEBURTS
    -1.09
    Manbalar
    -1.07
    脚注の使い方
    -1.07
    Viitteet
    -1.07
    +#+#
    -1.04
    POSITIVE LOGITS
    y
    1.71
    i
    1.67
    o
    1.63
    a
    1.50
    e
    1.41
    ه
    1.37
    s
    1.32
    ی
    1.28
    er
    1.20
    t
    1.16
    Activations Density 2.321%

    No Known Activations