© 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. 1716
    Prev
    Next
    INDEX
    Explanations

    statements about consistency and agreements in research findings

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

    Following "is" or similar words like "consistent" or "keeping"

    np_acts-logits-general · gemini-2.0-flash

    consistent with

    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
    XmlAccessType
    -0.68
    InjectAttribute
    -0.67
    ftagPool
    -0.64
    StructEnd
    -0.64
     []:
    -0.64
     OFDb
    -0.63
    Rohy
    -0.62
    енча
    -0.62
     kasarigan
    -0.61
    AppCompatTheme
    -0.59
    POSITIVE LOGITS
     consistent
    1.00
    consistent
    0.91
     par
    0.89
    Consistent
    0.88
     Consistent
    0.87
     acorde
    0.79
     aligns
    0.78
     consistency
    0.72
     aligned
    0.71
     inline
    0.70
    Activations Density 0.274%

    No Known Activations