© 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. 1-GEMMASCOPE-RES-16K
    6. 5204
    Prev
    Next
    INDEX
    Explanations

    repeated phrases or terms labeled as 'case' within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ėjimas
    -0.52
     stili
    -0.48
    ılmaz
    -0.47
    Der
    -0.46
     Vale
    -0.46
    irmanship
    -0.44
    utat
    -0.44
     इस्तेमाल
    -0.43
     raggiunto
    -0.43
    ogia
    -0.43
    POSITIVE LOGITS
    RegressionTest
    1.01
    %");
    0.98
     snippetHide
    0.87
    =$?
    0.86
    "});
    0.84
    ]--;
    0.84
     ExecuteAsync
    0.83
    <>());
    0.83
     {}));
    0.82
    }');
    0.81
    Activations Density 0.137%

    No Known Activations