© 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. 8354
    Prev
    Next
    INDEX
    Explanations

    negative aspects related to fees, requirements, or charges associated with services and products

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

    Absence, negation, or lack of something

    np_acts-logits-general · gemini-2.0-flash

    no x whatsoever

    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
    ynchronously
    -0.66
     ſome
    -0.64
    もう少し
    -0.63
    tvguidetime
    -0.62
    Certain
    -0.61
    aspectj
    -0.60
     ſeveral
    -0.59
     BioLib
    -0.57
     Alcalde
    -0.56
    Algunas
    -0.56
    POSITIVE LOGITS
     whatsoever
    1.45
     nor
    1.34
     nicio
    1.05
     apapun
    1.02
     nenhuma
    1.02
     any
    1.01
    ใด
    1.00
     nenhum
    0.98
     or
    0.97
     alcuna
    0.97
    Activations Density 0.574%

    No Known Activations