© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 5253
    Prev
    Next
    INDEX
    Explanations

    emphasis markers or quotes in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </b>
    -2.09
    </i>
    -1.44
    <b>
    -1.10
    dfrac
    -1.09
    <i>
    -0.80
     Phry
    -0.77
     Arxivat
    -0.77
    َّ
    -0.75
    例文帳に追加
    -0.73
     Prussian
    -0.72
    POSITIVE LOGITS
    <em>
    2.28
    </em>
    2.17
    </strong>
    1.59
     fl
    1.18
    fl
    1.13
     
    1.10
     """
    1.04
    """
    1.03
     first
    0.99
    fi
    0.99
    Activations Density 0.145%

    No Known Activations