Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 16061
    Prev
    Next
    INDEX
    Explanations

    annotations and metadata in code, particularly related to components and configurations

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

    Code annotations (e.g. @interface, @IBAction)

    np_acts-logits-general · gemini-2.0-flash

    code directives and keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſch
    -0.59
     ſever
    -0.52
     juſ
    -0.51
     reaſon
    -0.50
    WEBPACK
    -0.49
    ſelf
    -0.49
     raiſ
    -0.49
    PYX
    -0.48
    Hochspringen
    -0.48
     purpoſe
    -0.48
    POSITIVE LOGITS
    ])))
    0.46
    ])));
    0.45
    ])).
    0.43
     noDo
    0.43
    InstrumentedTest
    0.42
    )))));
    0.41
     veck
    0.40
     });
    0.40
    )))))
    0.39
     }));
    0.39
    Activations Density 0.066%

    No Known Activations