© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 448
    Prev
    Next
    INDEX
    Explanations

    legal terms and conditions related to partnerships and regulations

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

    Code-related text, likely programming

    np_acts-logits-general · gemini-2.0-flash

    biased the frequency

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </i>
    -0.67
     betweenstory
    -0.61
    oredCriteria
    -0.51
    </b>
    -0.51
     estekak
    -0.48
    FieldNumber
    -0.48
     كورة
    -0.47
    Mant
    -0.45
    assertRaises
    -0.44
    protoc
    -0.44
    POSITIVE LOGITS
    TagMode
    0.99
    تقاوى
    0.77
     AspNetCore
    0.74
    )":
    0.70
    MigrationBuilder
    0.68
    󠁮
    0.68
     AssemblyProduct
    0.68
    </strong>
    0.68
    ]-->
    0.68
    )':
    0.67
    Activations Density 6.294%

    No Known Activations