© 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. 35-GEMMASCOPE-RES-16K
    11. 9818
    Prev
    Next
    INDEX
    Explanations

    terms related to the presence or absence of specific substances in experimental contexts

    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
     dikem
    -0.31
    anho
    -0.30
    ioutil
    -0.28
    SysUser
    -0.27
    แล้ว
    -0.27
    قایناقلار
    -0.27
    pijama
    -0.27
     duur
    -0.27
    kilo
    -0.26
    deutschen
    -0.26
    POSITIVE LOGITS
     presence
    3.66
    presence
    3.30
     Presence
    3.19
    Presence
    3.11
     présence
    3.02
     presencia
    2.94
     присут
    2.80
     presença
    2.77
     presenza
    2.75
     aanwezig
    2.58
    Activations Density 1.267%

    No Known Activations