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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 12-GEMMASCOPE-RES-16K
    6. 15466
    Prev
    Next
    INDEX
    Explanations

    programming syntax and structure, particularly related to function declarations and expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </strong>
    -0.68
    +#+#
    -0.61
    </u>
    -0.58
     Exacts
    -0.57
     NDEBUG
    -0.55
    </b>
    -0.55
    VertexAttrib
    -0.53
    TagMode
    -0.52
    interopRequire
    -0.52
    </em>
    -0.51
    POSITIVE LOGITS
    )))),
    1.07
    )))))
    0.88
    @[+][
    0.76
    ']))
    0.76
    ))),
    0.75
    Hozzáférés
    0.74
    .*")]
    0.73
    ))).
    0.73
    ']),
    0.73
    styleType
    0.73
    Activations Density 1.503%

    No Known Activations