© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 12476
    Prev
    Next
    INDEX
    Explanations

    chemical compounds and their concentrations

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

    Chemical symbols and subscripts

    np_acts-logits-general · gemini-2.0-flash

    chemical formula subscripts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    complexType
    -0.48
    /******/
    -0.48
    ьаж
    -0.47
    }}^
    -0.45
    FRIEND
    -0.44
     Hut
    -0.43
    RTEX
    -0.43
     coat
    -0.42
    ánto
    -0.42
    ConstraintMaker
    -0.42
    POSITIVE LOGITS
    <sub>
    1.53
    _{
    1.33
    }_{
    1.23
     _{
    1.22
     }_{
    1.15
     $_{
    1.12
    $_{
    1.11
    _{\
    1.10
    }_{\
    1.02
    "_
    1.00
    Activations Density 2.186%

    No Known Activations