© 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. 0-GEMMASCOPE-RES-16K
    6. 8281
    Prev
    Next
    INDEX
    Explanations

    the term "settle" and its variations, indicating a focus on resolutions or agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ang
    -0.53
    ay
    -0.51
    map
    -0.50
     spot
    -0.50
    od
    -0.49
    ij
    -0.49
    ng
    -0.48
    note
    -0.47
    1
    -0.47
    z
    -0.47
    POSITIVE LOGITS
    __':
    
    1.11
     Савезне
    1.09
    djangoproject
    1.09
    extAlignment
    1.03
     saites
    1.02
    overall
    0.99
    dafx
    0.98
    UnusedPrivate
    0.96
     Overall
    0.95
    autoreleasepool
    0.95
    Activations Density 0.159%

    No Known Activations