Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 15398
    Prev
    Next
    INDEX
    Explanations

    geographic and location-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pageContext
    -0.65
     Clown
    -0.53
     Laub
    -0.48
    UserScript
    -0.48
     fieldNum
    -0.48
    textLabel
    -0.47
     Alb
    -0.47
    )))),
    -0.47
    __::
    -0.47
    astify
    -0.47
    POSITIVE LOGITS
     bookId
    0.60
    Skye
    0.53
    farin
    0.52
     Skye
    0.52
     Moab
    0.51
     FormsModule
    0.51
     Enix
    0.50
     mCurrent
    0.50
    Wyoming
    0.49
    DotNetBar
    0.49
    Activations Density 1.347%

    No Known Activations