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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 13-GEMMASCOPE-RES-16K
    6. 6566
    Prev
    Next
    INDEX
    Explanations

    patterns that denote sections or categories within data

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

    formatted tabular or columnar numeric data (e.g., matrices, tables, and aligned figures in code/output).

    oai_token-act-pair · gpt-5Triggered by @arielgoldsteinlab
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AttributeSet
    -0.58
    stylesheet
    -0.57
     <<<<<<<<<<<<<<
    -0.57
    /**
    -0.53
    >>()
    -0.53
    /*++
    -0.50
    ioli
    -0.50
    esModule
    -0.48
    pragma
    -0.47
    Бахар
    -0.46
    POSITIVE LOGITS
     оригіналу
    0.74
    delwed
    0.64
    QMetaType
    0.64
    发表于
    0.62
    AndroidJUnit
    0.61
    photobucket
    0.60
     تضيفلها
    0.58
    wikk
    0.56
    fvar
    0.56
    󠁢
    0.56
    Activations Density 0.543%

    No Known Activations