© 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. 3-GEMMASCOPE-RES-16K
    11. 10605
    Prev
    Next
    INDEX
    Explanations

    terms related to measurement and dimensions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gynhyrchwyd
    -0.47
    /*++
    -0.46
    IBAction
    -0.44
     Roskov
    -0.44
    الدراسه
    -0.43
     ProtoMessage
    -0.42
     nakalista
    -0.42
    WebMethod
    -0.40
     '{@
    -0.40
    AccessorTable
    -0.40
    POSITIVE LOGITS
    len
    1.13
    lens
    1.07
    Len
    1.02
    Lens
    1.01
     Len
    0.97
     LEN
    0.96
    LEN
    0.96
     lens
    0.93
     Lens
    0.90
     len
    0.85
    Activations Density 1.252%

    No Known Activations