© 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. 14-GEMMASCOPE-RES-16K
    11. 5914
    Prev
    Next
    INDEX
    Explanations

    instances of the word "access" and related phrases indicating availability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/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.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     informes
    -0.39
     Investigaciones
    -0.35
     Bohn
    -0.35
     Hohen
    -0.35
     Maul
    -0.33
     originais
    -0.33
    lative
    -0.32
    Nouvelle
    -0.32
    VARIANT
    -0.31
    Brand
    -0.30
    POSITIVE LOGITS
     Access
    1.70
    access
    1.69
     access
    1.68
     ACCESS
    1.60
    Access
    1.60
    ACCESS
    1.54
     accesses
    1.37
     accessed
    1.24
     accessing
    1.24
    Accessing
    1.23
    Activations Density 0.066%

    No Known Activations