© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 15232
    Prev
    Next
    INDEX
    Explanations

    references to scientific or medical terminology related to deficiencies or specific strains in research contexts

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

    Absence, lack, removal

    np_acts-logits-general · gemini-2.0-flash

    absence or lack

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pinulongan
    -0.53
    balleur
    -0.51
    صلاح
    -0.50
    putAll
    -0.50
     vyš
    -0.48
    yntaxException
    -0.47
    moveToNext
    -0.47
    utilisons
    -0.46
    Nuorodos
    -0.46
    +#+
    -0.46
    POSITIVE LOGITS
     absence
    1.20
    absence
    1.08
     Absence
    1.04
     lack
    1.01
     devoid
    1.00
    Absence
    0.97
     отсутствие
    0.96
     omission
    0.95
     removed
    0.90
    lack
    0.89
    Activations Density 1.784%

    No Known Activations