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. 11-GEMMASCOPE-RES-16K
    6. 13697
    Prev
    Next
    INDEX
    Explanations

    specific symbols or formatting in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ידי
    -0.48
    </em>
    -0.46
    showAlert
    -0.45
    astéro
    -0.45
     –
    -0.45
     compañía
    -0.44
     đua
    -0.41
    <strong>
    -0.40
    Kariera
    -0.40
    றை
    -0.40
    POSITIVE LOGITS
    Personendaten
    1.03
    GEBURTSDATUM
    0.82
    tvguidetime
    0.81
    <bos>
    0.79
    UnsafeEnabled
    0.76
     ModelExpression
    0.73
    IUrlHelper
    0.70
    richTextPanel
    0.67
    Portail
    0.67
     '\\;'
    0.67
    Activations Density 0.552%

    No Known Activations