Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 7288
    Prev
    Next
    INDEX
    Explanations

    occurrences of identifiers or references in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     resourceCulture
    -0.51
    });*/
    -0.49
    })*/
    -0.44
    //});
    -0.44
    bida
    -0.44
    =<?
    -0.43
    )++;
    -0.42
    },[])
    -0.42
     BEST
    -0.40
     meilleurs
    -0.39
    POSITIVE LOGITS
     nakalista
    0.87
    脚注の使い方
    0.81
    存于互联网档案馆
    0.79
    Geplaatst
    0.75
    jsonwebtoken
    0.73
     GetEnumerator
    0.73
     disambiguazione
    0.70
    Seznam
    0.69
     Перейти
    0.68
    httphttps
    0.68
    Activations Density 0.019%

    No Known Activations