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. 12472
    Prev
    Next
    INDEX
    Explanations

    symbols and characters frequently used in programming 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
     asmen
    -0.48
    เข
    -0.46
     pengalaman
    -0.46
     l
    -0.44
    ip
    -0.43
     bevol
    -0.41
     })
    -0.41
    кен
    -0.41
    gues
    -0.41
    일
    -0.40
    POSITIVE LOGITS
    (!__
    0.99
    RectangleBorder
    0.88
    帖最后由
    0.84
     Theſe
    0.82
    errHandler
    0.82
    msgTypes
    0.82
    TagHelper
    0.81
     مشين
    0.80
    zzleHttp
    0.78
    AutoScaleMode
    0.77
    Activations Density 0.122%

    No Known Activations