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. 14-GEMMASCOPE-RES-16K
    6. 2892
    Prev
    Next
    INDEX
    Explanations

    elements related to user interface buttons and their enabling or disabling logic

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    verifyException
    -0.71
    MemoryWarning
    -0.71
    ########.
    -0.69
     виправивши
    -0.65
     estekak
    -0.63
    Bioaccumulative
    -0.60
    XmlAccessorType
    -0.60
    BindingResult
    -0.59
    rrggbb
    -0.58
     useParams
    -0.58
    POSITIVE LOGITS
     available
    0.68
    +#+#
    0.66
     menu
    0.64
    OptionsMenu
    0.61
     offering
    0.57
     options
    0.55
     offered
    0.55
    available
    0.55
     disponibile
    0.54
     Available
    0.54
    Activations Density 0.454%

    No Known Activations