© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 564
    Prev
    Next
    INDEX
    Explanations

    Java and programming-related constructs specifically focused on data types and value assignments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    würdig
    -0.39
     yanlış
    -0.38
    MockBean
    -0.38
    gezogen
    -0.37
    principalColumn
    -0.36
     getan
    -0.34
     Magdal
    -0.32
     Oeste
    -0.32
     aprobado
    -0.32
     peuples
    -0.31
    POSITIVE LOGITS
     propOrder
    0.68
     MAX
    0.65
    MaxValue
    0.65
     INT
    0.64
    MAX
    0.63
    MessageOf
    0.62
     maxim
    0.61
     getMax
    0.60
    StructEnd
    0.60
     maxValue
    0.59
    Activations Density 0.618%

    No Known Activations