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. 25-GEMMASCOPE-RES-16K
    6. 3969
    Prev
    Next
    INDEX
    Explanations

    references to neurotrophic factors and their effects on mental health

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bēr
    -0.89
     $<$
    -0.88
     [\
    -0.85
     (\
    -0.85
     varandra
    -0.83
     &#
    -0.82
     feroit
    -0.81
     démocr
    -0.79
     pouvoit
    -0.78
     soldati
    -0.77
    POSITIVE LOGITS
    ’?
    0.72
    “:
    0.65
     ané
    0.64
    ”?
    0.64
    “.
    0.62
    ”!
    0.62
    :'
    0.61
    '?
    0.61
    ंदीखरीदारी
    0.61
     indiri
    0.60
    Activations Density 0.095%

    No Known Activations