© 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. 25-GEMMASCOPE-RES-16K
    11. 1314
    Prev
    Next
    INDEX
    Explanations

    evaluative adjectives and descriptors that characterize objects or experiences

    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
     the
    -1.19
     CreateTagHelper
    -0.93
     its
    -0.91
     both
    -0.89
     their
    -0.88
     this
    -0.87
     some
    -0.86
     basically
    -0.86
     those
    -0.85
     our
    -0.83
    POSITIVE LOGITS
    ,
    1.04
    ly
    0.98
    ized
    0.88
     but
    0.87
    yet
    0.86
     yet
    0.80
    but
    0.77
     pero
    0.76
    ally
    0.74
     and
    0.72
    Activations Density 2.898%

    No Known Activations