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. 8748
    Prev
    Next
    INDEX
    Explanations

    instances of control flow keywords related to continuation or exception handling

    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
     “
    -0.54
     form
    -0.51
    /
    -0.51
    -
    -0.51
    ’
    -0.49
    </b>
    -0.49
     ());
    -0.48
    +}$
    -0.47
     B
    -0.47
     cent
    -0.46
    POSITIVE LOGITS
     poffe
    1.12
     purpoſe
    1.12
     themſelves
    1.09
    IntoConstraints
    1.08
     houſe
    1.05
     zelve
    1.04
     pleaſure
    1.02
     ſtate
    1.01
     myſelf
    1.01
    continue
    1.01
    Activations Density 0.015%

    No Known Activations