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. 15391
    Prev
    Next
    INDEX
    Explanations

    structured programming code and technical elements

    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
    UnsafeEnabled
    -0.64
    MessageState
    -0.61
    TagMode
    -0.60
    Cartney
    -0.58
    CloseOperation
    -0.57
     referrerpolicy
    -0.56
    +:+
    -0.56
     Walkover
    -0.56
    abestanden
    -0.55
    msgTypes
    -0.54
    POSITIVE LOGITS
    Portale
    1.08
    بوابة
    0.85
    Portail
    0.82
     combineReducers
    0.67
    žius
    0.60
     carottes
    0.55
    ChildIndex
    0.55
    rmtree
    0.55
     onlyOwner
    0.54
     Portail
    0.51
    Activations Density 0.239%

    No Known Activations