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. 7-GEMMASCOPE-RES-16K
    6. 11623
    Prev
    Next
    INDEX
    Explanations

    sections of code or documentation that indicate the beginning and end of code blocks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ة
    -0.82
    </b>
    -0.81
    o
    -0.75
    </i>
    -0.72
    a
    -0.69
     Elsie
    -0.68
    ETO
    -0.66
    es
    -0.66
    <b>
    -0.65
     Hert
    -0.63
    POSITIVE LOGITS
     """
    1.25
    """
    1.23
    ."""
    1.12
     MonoBehaviour
    1.06
     InputDecoration
    1.06
    featureID
    1.00
    GraphicsUnit
    1.00
    RenderAtEndOf
    1.00
    ("""
    0.99
    IsContent
    0.99
    Activations Density 0.135%

    No Known Activations