© 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-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 10462
    Prev
    Next
    INDEX
    Explanations

    text that discusses evaluations and analyses of various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    followed by "that"

    np_acts-logits-general · gemini-2.0-flash

    stated, estimated, reported information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 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
    AnimationsModule
    -0.52
    \{\\
    -0.50
     autorytatywna
    -0.50
    ArgsConstructor
    -0.47
    getSeconds
    -0.47
     kaarangay
    -0.46
    SharedCtor
    -0.45
     defaultstate
    -0.45
    initComponents
    -0.45
    DidLoad
    -0.44
    POSITIVE LOGITS
    ngdoc
    0.53
    úly
    0.45
    ropol
    0.44
     adulta
    0.38
    bre
    0.37
    ByExample
    0.37
     famous
    0.37
    AddHtmlAttribute
    0.35
     famously
    0.35
    tiek
    0.35
    Activations Density 1.404%

    No Known Activations