© 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. 8292
    Prev
    Next
    INDEX
    Explanations

    references to contrasting conditions or situations

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

    that often precede quantities or groups

    np_acts-logits-general · gemini-2.0-flash

    some and many

    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
    érité
    -0.56
    OGND
    -0.55
    IsContent
    -0.54
     незавершена
    -0.54
    脚注の使い方
    -0.53
     Efq
    -0.52
    NameValuePair
    -0.50
    一共
    -0.48
    Superview
    -0.47
    zellan
    -0.47
    POSITIVE LOGITS
     certains
    2.42
     some
    2.42
     algunos
    2.29
     некоторых
    2.23
     certain
    2.23
     certaines
    2.23
     sommige
    2.20
     niektórych
    2.17
     некоторые
    2.16
     algunas
    2.15
    Activations Density 1.015%

    No Known Activations