© 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-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 8888
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to safety and risk assessment in various contexts

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

    after indications of safety

    np_acts-logits-general · gemini-2.0-flash

    safety and security

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    penup
    -0.51
    rativa
    -0.51
    usermodel
    -0.51
    graphicx
    -0.48
    VIAF
    -0.48
    XmlAccessType
    -0.47
     Exactos
    -0.47
    nodoc
    -0.47
    esModule
    -0.47
     nonUne
    -0.46
    POSITIVE LOGITS
     safety
    3.53
     safe
    3.20
    safety
    3.13
     Safety
    3.02
    Safety
    2.99
     safer
    2.91
    safe
    2.90
     safely
    2.86
     SAFETY
    2.81
     safest
    2.79
    Activations Density 0.275%

    No Known Activations