© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 8912
    Prev
    Next
    INDEX
    Explanations

    indications of starting or initiating actions or events

    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
     []:
    -0.67
    :"-"`
    -0.59
     passada
    -0.53
    ις
    -0.51
    occasione
    -0.51
     referrerpolicy
    -0.49
    Naissance
    -0.48
    skb
    -0.48
    LoS
    -0.48
    SuspendLayout
    -0.47
    POSITIVE LOGITS
     afresh
    0.93
     anew
    0.75
    AndEndTag
    0.74
    ต้น
    0.73
     fresh
    0.65
    seite
    0.63
     codon
    0.61
    OfWeek
    0.60
    tvguidetime
    0.58
     snippetHide
    0.55
    Activations Density 0.137%

    No Known Activations