© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 13107
    Prev
    Next
    INDEX
    Explanations

    specific location references, such as addresses and place names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    usermodel
    -0.80
    ValueStyle
    -0.76
    principalTable
    -0.73
     propOrder
    -0.72
    LookAnd
    -0.69
    setVerticalGroup
    -0.65
    endphp
    -0.63
     referrerpolicy
    -0.61
     <=",
    -0.61
    setViewportView
    -0.60
    POSITIVE LOGITS
    ADDRESS
    0.50
     hasattr
    0.50
    Filmographie
    0.49
    sidemargin
    0.47
    żą
    0.46
    новништво
    0.45
     rue
    0.44
     Fleming
    0.44
    httphttps
    0.43
    lapse
    0.43
    Activations Density 0.075%

    No Known Activations