© 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. 11034
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate the inclusion of additional information or points

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

    "Besides" or similar introductory words

    np_acts-logits-general · gemini-2.0-flash

    besides being

    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
    standigheden
    -0.57
     resourceCulture
    -0.55
     instead
    -0.55
    ITHER
    -0.54
     wikipagina
    -0.54
    gatsby
    -0.54
     omge
    -0.53
    sequent
    -0.52
    JspWriter
    -0.52
    WebElementEntity
    -0.52
    POSITIVE LOGITS
     being
    0.94
    being
    0.79
    Being
    0.71
    Portail
    0.66
     disambiguazione
    0.65
    NameInMap
    0.65
     obvious
    0.64
     BEING
    0.64
    enumi
    0.63
     Being
    0.62
    Activations Density 0.116%

    No Known Activations