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. 5-GEMMASCOPE-RES-16K
    6. 11137
    Prev
    Next
    INDEX
    Explanations

    phrases related to the ability to perform tasks or responsibilities, particularly in contexts involving qualifications and support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itoneum
    -0.61
    aarrggbb
    -0.58
    ёх
    -0.52
    SOUNDBITE
    -0.49
    ofold
    -0.49
    MessageOf
    -0.48
    ellees
    -0.47
    RenderAtEndOf
    -0.47
    IARC
    -0.47
    $_['
    -0.47
    POSITIVE LOGITS
     capable
    0.62
     referenties
    0.62
    capable
    0.60
     capability
    0.59
     capacity
    0.58
     Enough
    0.57
     الاطلاع
    0.57
    Enough
    0.57
     propOrder
    0.57
     Capability
    0.56
    Activations Density 0.345%

    No Known Activations