© 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-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 16375
    Prev
    Next
    INDEX
    Explanations

    references to political constituencies and electoral regions

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

    Followed by capitalized words

    np_acts-logits-general · gemini-2.0-flash

    of followed by places or names

    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
     Scottish
    -0.54
     Scotland
    -0.50
     Glasgow
    -0.46
    MEMORANDUM
    -0.45
     Harm
    -0.44
    áctenos
    -0.44
     harm
    -0.43
    Glasgow
    -0.42
    scot
    -0.42
    Scotland
    -0.40
    POSITIVE LOGITS
    脚注の使い方
    0.83
     propOrder
    0.77
    principalTable
    0.76
    ValueStyle
    0.74
    +#+#
    0.70
    الدراسه
    0.70
    findpost
    0.69
    })*/
    0.65
    StoreMessageInfo
    0.64
    PyTuple
    0.63
    Activations Density 0.164%

    No Known Activations