Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 3102
    Prev
    Next
    INDEX
    Explanations

    terms associated with interception and surveillance activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     trekken
    -0.48
     peine
    -0.46
    gione
    -0.44
     tarto
    -0.44
    коно
    -0.42
     recommandée
    -0.42
     tqdm
    -0.41
     modelli
    -0.40
    SetBool
    -0.40
     precisam
    -0.40
    POSITIVE LOGITS
     intercept
    1.01
     intercepted
    1.00
     eaves
    0.96
     hack
    0.89
     intercepts
    0.88
     hijack
    0.86
     overheard
    0.82
    AndEndTag
    0.82
     interception
    0.80
    intercept
    0.79
    Activations Density 0.991%

    No Known Activations