© 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. 8154
    Prev
    Next
    INDEX
    Explanations

    words related to connections or links between concepts

    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
    <eos>
    -0.51
     
    -0.51
     you
    -0.49
    mathrm
    -0.48
     just
    -0.47
    2
    -0.46
     our
    -0.45
     I
    -0.44
    1
    -0.44
     "
    -0.43
    POSITIVE LOGITS
    <bos>
    1.24
    aarrggbb
    0.97
    ])));
    0.95
     CURIAM
    0.92
     ModelExpression
    0.91
    ✨:
    0.90
    tagHelperRunner
    0.89
    $_['
    0.88
    RegressionTest
    0.87
    )))));
    0.86
    Activations Density 0.831%

    No Known Activations