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. 8114
    Prev
    Next
    INDEX
    Explanations

    references to progress, change, and forward movement in various contexts

    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
    adaptiveStyles
    -0.64
    Personensuche
    -0.62
    XmlAccessorType
    -0.60
     TestBed
    -0.59
     lenker
    -0.59
    BeginContext
    -0.59
     initComponents
    -0.59
     consultato
    -0.56
     Ause
    -0.56
    ppelin
    -0.53
    POSITIVE LOGITS
     forward
    3.09
    forward
    2.54
     Forward
    2.35
    Forward
    2.31
     FORWARD
    2.23
     forwards
    2.12
    FORWARD
    1.88
     fwd
    1.70
     forwarding
    1.66
     вперед
    1.64
    Activations Density 0.386%

    No Known Activations