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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 6068
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and variables related to equations and statistical modeling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BeginContext
    -0.60
    TagMode
    -0.58
    ภัย
    -0.53
     hukum
    -0.53
    >';
    -0.52
    uxxxx
    -0.51
    },
    
    -0.50
    AutoScaleMode
    -0.50
    routeProvider
    -0.49
    KURZBESCHREIBUNG
    -0.49
    POSITIVE LOGITS
     Majefty
    0.84
     houſe
    0.78
     Houſe
    0.75
    enderror
    0.75
     itſelf
    0.75
     Efq
    0.74
     purpoſe
    0.74
    ^(@)
    0.73
     ſever
    0.70
     ſta
    0.69
    Activations Density 0.471%

    No Known Activations