© 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. 4114
    Prev
    Next
    INDEX
    Explanations

    programming language syntax elements and structures

    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
     Jefus
    -0.97
    NewUrlParser
    -0.96
     nakalista
    -0.87
     myſelf
    -0.83
    paravant
    -0.82
     kasarigan
    -0.79
     Chriftian
    -0.79
    ſelves
    -0.79
     houſe
    -0.78
     Efq
    -0.78
    POSITIVE LOGITS
     le
    0.55
    zu
    0.54
    Tr
    0.53
    <eos>
    0.52
    eci
    0.51
     Abs
    0.51
     Tr
    0.49
    iles
    0.49
    Hozzáférés
    0.49
    uerre
    0.49
    Activations Density 0.032%

    No Known Activations