© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 31-GEMMASCOPE-RES-16K
    11. 4988
    Prev
    Next
    INDEX
    Explanations

    terms related to destruction and damage, particularly in the context of evidence, property, and testing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    words related to destruction, damage, or violent harm to objects and property.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.45
    LabelTagHelper
    -0.38
    jdt
    -0.34
    PreInfinity
    -0.34
    PostInfinity
    -0.34
    Jeografia
    -0.33
    ولايات
    -0.33
     capucha
    -0.30
     PopupWindow
    -0.30
     Glieder
    -0.30
    POSITIVE LOGITS
     destruction
    2.28
     destroy
    2.08
     Destruction
    2.06
     destroying
    2.03
     destroyed
    2.00
     Destroy
    1.97
     destru
    1.91
    Destruction
    1.91
     destroys
    1.91
    destruction
    1.88
    Activations Density 0.449%

    No Known Activations