© 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. 24-GEMMASCOPE-RES-16K
    11. 8009
    Prev
    Next
    INDEX
    Explanations

    phrases and structures indicating possession or ownership

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

    the possessive form of pronouns indicated by contractions ending with "'s".

    oai_token-act-pair · gpt-4oTriggered by @thinkspring96

    A word ending with an apostrophe and then "s"

    np_acts-logits-general · gemini-2.0-flash

    s-prefix words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    centralwidget
    -0.52
     Protección
    -0.47
    (
    -0.42
     AutoMapper
    -0.40
    arnia
    -0.36
    Contr
    -0.36
    허
    -0.36
    ом
    -0.36
    0
    -0.36
     kans
    -0.35
    POSITIVE LOGITS
    sthe
    1.06
    sto
    1.04
    sso
    0.97
    simage
    0.97
    sex
    0.94
    sire
    0.90
    semp
    0.87
    ssent
    0.85
    spro
    0.84
    ss
    0.84
    Activations Density 0.446%

    No Known Activations