© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 9571
    Prev
    Next
    INDEX
    Explanations

    technical terms and mathematical symbols used in a formal analysis or theoretical context

    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
    "):
    -0.52
    ')):
    -0.52
    Giới
    -0.51
     )(
    -0.51
    '):
    -0.51
    </em>
    -0.49
    )):
    -0.49
    Manbalar
    -0.49
    ">"
    -0.48
     '.
    -0.48
    POSITIVE LOGITS
    setVerticalGroup
    0.69
     myſelf
    0.69
     natale
    0.69
     ditto
    0.67
     Monfieur
    0.66
    enumii
    0.66
     resourceCulture
    0.66
     poffe
    0.65
     Efq
    0.65
    ChildScrollView
    0.63
    Activations Density 0.796%

    No Known Activations