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. 7-GEMMASCOPE-RES-16K
    6. 5895
    Prev
    Next
    INDEX
    Explanations

    the structural elements of the text, including delimiters and formatting indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     تضيفلها
    -0.69
    ÁND
    -0.68
    İY
    -0.67
     highly
    -0.61
     décou
    -0.61
     sánchez
    -0.60
     sorts
    -0.59
    렇
    -0.59
    encu
    -0.59
    دانشنامهٔ
    -0.58
    POSITIVE LOGITS
     nakalista
    0.82
    HttpPut
    0.73
     rospy
    0.67
    !*\
    0.66
    ManagedBean
    0.66
    RenderAtEndOf
    0.65
    abstractmethod
    0.65
    parsedMessage
    0.64
    __":
    
    0.64
     Designers
    0.64
    Activations Density 0.267%

    No Known Activations