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. 12262
    Prev
    Next
    INDEX
    Explanations

    occurrences of line break tags in HTML code

    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
     AssemblyCulture
    -0.82
    }))
    
    -0.80
    ()")
    -0.72
    })).
    -0.72
     المعيارى
    -0.67
    EndProject
    -0.66
    <>("
    -0.66
    İstinadlar
    -0.65
     '\\;'
    -0.65
    }}"
    -0.65
    POSITIVE LOGITS
    br
    1.98
     br
    1.03
    Br
    0.88
    BR
    0.83
     Br
    0.71
    tr
    0.66
    nbsp
    0.62
    fetchall
    0.57
    hr
    0.55
    gr
    0.54
    Activations Density 0.051%

    No Known Activations