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. 9-GEMMASCOPE-RES-16K
    6. 15254
    Prev
    Next
    INDEX
    Explanations

    function calls related to data encoding and decoding processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ath
    -0.61
    MigrationBuilder
    -0.59
     context
    -0.58
    FirebaseAuth
    -0.58
    Ath
    -0.55
    amaño
    -0.55
    PathVariable
    -0.54
    
    -0.54
    ถ
    -0.52
     Etr
    -0.50
    POSITIVE LOGITS
    stringify
    1.78
    UrlResolution
    1.23
    encode
    1.15
    decode
    1.02
     AssemblyVersion
    0.96
     encode
    0.96
     Decode
    0.94
     encoded
    0.91
    encoded
    0.91
    Decode
    0.87
    Activations Density 0.036%

    No Known Activations