© 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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 87345
    Prev
    Next
    INDEX
    Explanations

    sections or headings that introduce important content or sections in a document

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

    section titles or labels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pecabe
    -0.82
    RenderAtEndOf
    -0.78
     desmotivaciones
    -0.75
     дописавши
    -0.71
    iſen
    -0.70
     saveiro
    -0.68
     betweenstory
    -0.68
    rrggbb
    -0.68
     ganchillo
    -0.68
    aarrggbb
    -0.67
    POSITIVE LOGITS
    </strong>
    0.81
    </em>
    0.72
    :
    0.71
    >):
    0.69
    </sup>
    0.65
    </b>
    0.63
    :]:
    0.61
    ]:
    0.60
    })));
    0.59
    ]]:
    0.59
    Activations Density 0.002%

    No Known Activations