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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 6250
    Prev
    Next
    INDEX
    Explanations

    concepts related to online security threats and phishing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ideal
    -0.41
    ↵↵
    -0.38
    ,
    -0.37
     row
    -0.36
     ten
    -0.36
     chapter
    -0.35
     "
    -0.34
    1
    -0.34
    .
    -0.34
     width
    -0.33
    POSITIVE LOGITS
    Hentet
    0.84
     CreateTagHelper
    0.82
    EndContext
    0.77
    UserScript
    0.76
     kasarigan
    0.76
    majánló
    0.76
    yntaxException
    0.75
     estekak
    0.73
     vooz
    0.72
    ագրություններ
    0.72
    Activations Density 0.179%

    No Known Activations