© 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. 7-GEMMASCOPE-RES-16K
    11. 13653
    Prev
    Next
    INDEX
    Explanations

    the word "inside" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VolleyError
    -0.52
    ptăm
    -0.48
     ThemeData
    -0.48
     toalha
    -0.47
     preghiera
    -0.45
    SBATCH
    -0.45
     africains
    -0.44
     namorados
    -0.44
     avoient
    -0.44
     frango
    -0.44
    POSITIVE LOGITS
     inside
    2.67
    inside
    2.58
    Inside
    2.56
     Inside
    2.53
     INSIDE
    2.31
    INSIDE
    2.13
     внутри
    1.56
     داخل
    1.47
    outside
    1.45
     Outside
    1.42
    Activations Density 0.089%

    No Known Activations