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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 6-GEMMASCOPE-RES-16K
    6. 6201
    Prev
    Next
    INDEX
    Explanations

    numeric representations of system specifications or configurations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    text formatting elements like commas, colons, and list markers that structure content.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    environmentally sustainable practices and technologies.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ReusableCell
    -0.63
    setVerticalGroup
    -0.61
    ]--;
    -0.56
     BrowserModule
    -0.56
    fromnode
    -0.56
     Roskov
    -0.55
     ويكيپ
    -0.53
    ertion
    -0.50
     PeEn
    -0.50
    PerformLayout
    -0.49
    POSITIVE LOGITS
    <bos>
    3.25
     the
    0.67
    '
    0.58
    -
    0.54
     and
    0.53
     to
    0.51
    ’
    0.50
    is
    0.50
     it
    0.48
     that
    0.48
    Activations Density 38.520%

    No Known Activations