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. 4-GEMMASCOPE-RES-16K
    6. 3167
    Prev
    Next
    INDEX
    Explanations

    function calls and method names related to data retrieval and modification in code

    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
     Tia
    -0.98
     gynhyrchwyd
    -0.81
     OFDb
    -0.76
     Grimm
    -0.72
    '}>
    -0.71
     saites
    -0.71
     Luz
    -0.71
    meniz
    -0.69
    Tia
    -0.68
    IVEREF
    -0.68
    POSITIVE LOGITS
    Get
    1.29
     Get
    1.09
     GetAll
    0.91
     testGet
    0.91
     Diſ
    0.81
     eſt
    0.81
     Plin
    0.80
    GetAll
    0.78
     Inſ
    0.76
     iſt
    0.76
    Activations Density 0.196%

    No Known Activations