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. 15-GEMMASCOPE-RES-16K
    6. 12855
    Prev
    Next
    INDEX
    Explanations

    tags and elements commonly used in code, particularly related to Maven configuration files and programming structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,
    -0.69
    1
    -0.65
    -
    -0.64
    5
    -0.63
     
    -0.61
     (
    -0.60
    3
    -0.58
     in
    -0.58
    9
    -0.58
     and
    -0.57
    POSITIVE LOGITS
     houſe
    1.08
     Houſe
    1.01
     Majefty
    0.92
     wikipagina
    0.91
     Diſ
    0.89
    Portale
    0.86
     BoxDecoration
    0.85
     Efq
    0.85
    ſelf
    0.84
    ſelves
    0.82
    Activations Density 0.430%

    No Known Activations