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. 1-GEMMASCOPE-RES-16K
    6. 13606
    Prev
    Next
    INDEX
    Explanations

    verbal forms of the word "to become" or related forms in a legal or formal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Soit
    -0.60
     Pard
    -0.57
     theils
    -0.56
    ()?;
    -0.56
     Protobuf
    -0.56
    isAlive
    -0.56
    __*/
    -0.55
    };*/
    -0.55
     isEnabled
    -0.55
     insuffisamment
    -0.55
    POSITIVE LOGITS
     werden
    0.80
     wordt
    0.68
    htm
    0.64
     wird
    0.64
     werd
    0.63
    ivotopis
    0.62
    +#+#
    0.61
     worden
    0.60
    ControllerAdvice
    0.60
     getopt
    0.59
    Activations Density 0.065%

    No Known Activations