© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 1724
    Prev
    Next
    INDEX
    Explanations

    instances of the word "description."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __':
    -0.81
    Kjelder
    -0.72
    thenReturn
    -0.70
     Efq
    -0.68
    __':
    -0.68
    __":
    -0.67
    ::_('
    -0.67
    THEOREM
    -0.67
     Accesat
    -0.67
    Theorem
    -0.66
    POSITIVE LOGITS
     description
    3.45
    description
    3.02
     Description
    2.98
     descriptions
    2.91
    Description
    2.85
     DESCRIPTION
    2.65
    DESCRIPTION
    2.52
     Descriptions
    2.35
     descrip
    2.33
    descriptions
    2.30
    Activations Density 0.101%

    No Known Activations