© 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. 14742
    Prev
    Next
    INDEX
    Explanations

    phrases related to accuracy and correctness in various contexts

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

    Doing something wrong or right

    np_acts-logits-general · gemini-2.0-flash

    identifying things wrong

    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
    adpleegd
    -0.59
    єра
    -0.56
     namorado
    -0.45
    Sqft
    -0.45
     Wikimedijinoj
    -0.45
    Tore
    -0.43
     Cuen
    -0.43
    €/
    -0.43
    enumerable
    -0.43
    Ţ
    -0.42
    POSITIVE LOGITS
     wrong
    1.46
     correct
    1.38
     correctly
    1.33
    wrong
    1.26
    correct
    1.24
    Correct
    1.19
     incorrect
    1.17
     Correct
    1.16
     CORRECT
    1.14
     correctness
    1.13
    Activations Density 0.129%

    No Known Activations