© 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. 35-GEMMASCOPE-RES-16K
    11. 8503
    Prev
    Next
    INDEX
    Explanations

    references to freedom and constraints

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/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.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ppl
    -0.69
     (=
    -0.59
     Asimismo
    -0.58
    /
    -0.58
     např
    -0.55
     etc
    -0.53
     Hence
    -0.53
     &
    -0.53
     perciò
    -0.52
    hence
    -0.51
    POSITIVE LOGITS
    ロウィン
    0.90
    iſen
    0.88
    нгред
    0.86
    Tikang
    0.86
     imagui
    0.82
     queſta
    0.82
    ſicht
    0.82
    ſſung
    0.81
     wiſſen
    0.80
     Geiſt
    0.80
    Activations Density 0.489%

    No Known Activations