© 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. 8-GEMMASCOPE-RES-16K
    6. 6879
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "maximum" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     meds
    -0.74
     âgées
    -0.68
     beginnetje
    -0.62
     dépos
    -0.62
     Robb
    -0.62
     Myles
    -0.62
     STORY
    -0.61
    VENTORY
    -0.60
    thru
    -0.60
     виправивши
    -0.60
    POSITIVE LOGITS
    MAXIMUM
    0.97
    minimum
    0.97
    Minimum
    0.96
    Maximum
    0.93
    setMaximum
    0.93
    maximum
    0.93
     Maximum
    0.90
    setMinimum
    0.89
     MAXIMUM
    0.88
    cination
    0.88
    Activations Density 0.108%

    No Known Activations