© 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. 4-GEMMASCOPE-RES-16K
    11. 371
    Prev
    Next
    INDEX
    Explanations

    quantifiers and references to amounts or numbers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.66
    HORE
    -0.62
     esternos
    -0.61
    haustible
    -0.61
    Queryable
    -0.57
    Cyfarwyddwr
    -0.57
    Ivoire
    -0.57
    harapkan
    -0.56
    cuerdo
    -0.56
    annica
    -0.55
    POSITIVE LOGITS
    GOTREF
    0.64
    OGND
    0.64
    HomeAsUpEnabled
    0.51
     localVar
    0.50
     dominant
    0.47
    Coordenadas
    0.47
    <eos>
    0.46
    ναι
    0.46
    expandindo
    0.45
    '&:
    0.45
    Activations Density 0.491%

    No Known Activations