© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 12399
    Prev
    Next
    INDEX
    Explanations

    contexts involving threats and intimidation

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

    intimidation and threats

    np_acts-logits-general · gemini-2.0-flash

    intimidation and threats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fjspx
    -0.75
    ]--;
    -0.62
     referenties
    -0.59
    DropColumn
    -0.58
    Aiheesta
    -0.54
    thmus
    -0.51
    InputTagHelper
    -0.51
     مرئيه
    -0.51
    hyrchwyd
    -0.50
    كوم
    -0.49
    POSITIVE LOGITS
     intimidating
    1.47
     threatening
    1.45
     menacing
    1.33
     threats
    1.30
     intimidation
    1.29
     scaring
    1.29
     threat
    1.28
     intimidate
    1.25
     scary
    1.21
     intimid
    1.20
    Activations Density 0.292%

    No Known Activations