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. 22-GEMMASCOPE-RES-16K
    6. 5983
    Prev
    Next
    INDEX
    Explanations

    HTML and formatting tags within the text

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

    Code comments delimiters (/*) and HTML tags

    np_acts-logits-general · gemini-2.0-flash

    code and markup

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </strong>
    -1.26
    </em>
    -1.25
     fl
    -1.07
    <em>
    -1.06
    fl
    -1.01
    ",@"
    -0.91
    <strong>
    -0.89
     
    -0.87
    """
    
    -0.86
     """
    -0.83
    POSITIVE LOGITS
    </b>
    2.27
    </i>
    2.07
    <i>
    1.47
    <b>
    1.39
    dfrac
    1.14
    ']").
    0.96
    '>
    0.95
    </td>
    0.89
    '>"
    0.89
    %)$
    0.85
    Activations Density 0.129%

    No Known Activations