© 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. 18-GEMMASCOPE-RES-16K
    11. 9284
    Prev
    Next
    INDEX
    Explanations

    not exhibit significant activation on any specific terms or patterns in the provided text

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

    Code snippets or mathematical expressions

    np_acts-logits-general · gemini-2.0-flash

    articles, code, or lists

    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
    XmlAccessorType
    -0.53
    <eos>
    -0.43
    ")->
    -0.42
     inté
    -0.42
    big
    -0.41
    …
    -0.41
    ]>=
    -0.41
    ...
    -0.41
    StringCopy
    -0.40
    相手の
    -0.40
    POSITIVE LOGITS
    principalColumn
    0.74
    存于互联网档案馆
    0.69
    __':
    0.67
    RegressionTest
    0.67
     continúas
    0.66
    IContainer
    0.66
    __":
    0.66
    __':
    0.65
    vertisers
    0.65
    CompilerServices
    0.63
    Activations Density 0.308%

    No Known Activations