Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 6120
    Prev
    Next
    INDEX
    Explanations

    chemical compounds and their related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dillera
    -0.49
    namics
    -0.47
    собенности
    -0.45
    principalColumn
    -0.45
    rhosis
    -0.43
     nahilalakip
    -0.42
    rostis
    -0.41
     Allí
    -0.40
     đến
    -0.40
    iastes
    -0.40
    POSITIVE LOGITS
    ac
    2.11
    AC
    1.82
     ac
    1.53
    acs
    1.47
    ak
    1.40
     Ac
    1.38
    Ac
    1.33
     AC
    1.33
    ack
    1.28
    ach
    1.28
    Activations Density 1.989%

    No Known Activations