© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 187
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to research results and outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PointerException
    -0.61
    ialmente
    -0.60
    ConstraintMaker
    -0.59
    اطر
    -0.53
    PDM
    -0.53
    žių
    -0.53
    rupal
    -0.52
     morire
    -0.52
    rinfo
    -0.51
     hoor
    -0.51
    POSITIVE LOGITS
    antly
    0.72
     obtained
    0.70
    ant
    0.69
    ants
    0.66
    स्व
    0.65
     obtenidos
    0.64
     achieved
    0.63
    ats
    0.61
     erzielt
    0.60
     obtenu
    0.59
    Activations Density 0.269%

    No Known Activations