© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 13012
    Prev
    Next
    INDEX
    Explanations

    function calls and data retrieval operations in code

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

    Follows "content."/function "get"

    np_acts-logits-general · gemini-2.0-flash

    get followed by method or name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.76
    Tikang
    -0.68
    UnusedPrivate
    -0.58
    +#+#
    -0.57
    AddTagHelper
    -0.56
     հղումներ
    -0.55
    PyExc
    -0.53
     препратки
    -0.52
     useAppContext
    -0.52
    principalTable
    -0.52
    POSITIVE LOGITS
     actual
    0.41
     Pakistani
    0.38
    をもって
    0.37
     overall
    0.36
     accompanying
    0.35
     Pleasant
    0.35
     African
    0.35
     ehe
    0.34
    ieszka
    0.34
     Microsoft
    0.34
    Activations Density 0.072%

    No Known Activations