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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 6-GEMMASCOPE-RES-16K
    6. 3719
    Prev
    Next
    INDEX
    Explanations

    terms related to infiltration or intensive interactions within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    closePath
    -0.60
    bular
    -0.54
     Khalifa
    -0.53
     Allegretto
    -0.53
    odynamic
    -0.52
    hj
    -0.52
     fuo
    -0.52
     Computation
    -0.51
    berra
    -0.50
     Expression
    -0.50
    POSITIVE LOGITS
     infuse
    0.92
     nahilalakip
    0.88
     perme
    0.86
     perv
    0.84
     penetrated
    0.83
     impregn
    0.82
     infil
    0.82
     infused
    0.82
     infiltrated
    0.80
    AndEndTag
    0.80
    Activations Density 0.444%

    No Known Activations