© 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. 7-GEMMASCOPE-RES-16K
    11. 4743
    Prev
    Next
    INDEX
    Explanations

    elements that represent the start of a block of text or section in content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    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>
    -0.53
    ]";
    -0.52
    }*/
    -0.52
    Халык
    -0.48
     Jara
    -0.48
    IVEREF
    -0.47
    ("../../
    -0.45
    linien
    -0.45
    fähig
    -0.45
     Combined
    -0.44
    POSITIVE LOGITS
    migrationBuilder
    1.28
    Datuak
    0.83
    OGND
    0.82
    tagHelperRunner
    0.80
     CreateTagHelper
    0.80
    انجليز
    0.79
    ècie
    0.78
    Geplaatst
    0.78
    Personendaten
    0.78
     EconPapers
    0.77
    Activations Density 0.016%

    No Known Activations