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. 5-GEMMASCOPE-RES-16K
    6. 1997
    Prev
    Next
    INDEX
    Explanations

    pronouns and the presence of specific entities or subjects within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    XMLSchema
    -0.47
    ledad
    -0.46
     posteriori
    -0.46
     WaitForSeconds
    -0.45
    以上
    -0.40
    fällt
    -0.40
    JsonProperty
    -0.40
     forthcoming
    -0.39
     магни
    -0.39
    áneamente
    -0.38
    POSITIVE LOGITS
     where
    1.30
     donde
    1.15
    donde
    1.15
     Allí
    1.13
    where
    1.13
     Where
    1.11
     Donde
    1.10
     يتيمه
    1.09
    Donde
    1.07
     Où
    1.06
    Activations Density 0.204%

    No Known Activations