© 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. 7-GEMMASCOPE-RES-16K
    6. 9845
    Prev
    Next
    INDEX
    Explanations

    terms related to oscillation and fluctuation, especially in a repeating or alternating context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éril
    -0.50
     kon
    -0.47
    imread
    -0.46
    ########.
    -0.43
    here
    -0.43
    上位
    -0.42
    CONSOLE
    -0.42
    nél
    -0.42
     Lynn
    -0.42
     agarre
    -0.41
    POSITIVE LOGITS
     alternating
    1.26
     alternates
    1.10
     alternation
    1.09
     alternately
    1.05
     oscillating
    1.04
     fluctuation
    1.02
     fluctuate
    1.01
     fluctu
    1.00
     fluctuating
    0.98
    parsedMessage
    0.98
    Activations Density 0.433%

    No Known Activations