© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 14969
    Prev
    Next
    INDEX
    Explanations

    prepositions, particularly those indicating relationships or conditions in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Stirn
    -0.43
    SourceChecksum
    -0.38
    <>("
    -0.38
    DotNetBar
    -0.37
    /**
    -0.36
    %"),
    -0.35
    ]));
    -0.33
     zemi
    -0.32
    avance
    -0.32
    yczą
    -0.32
    POSITIVE LOGITS
     ||=
    0.70
    posedge
    0.66
    WriteTagHelper
    0.63
    Autoritní
    0.62
     +=
    0.62
     ∈
    0.60
     doInBackground
    0.60
    GIVEREF
    0.60
    NullException
    0.59
    ∈
    0.58
    Activations Density 0.194%

    No Known Activations