© 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. 3113
    Prev
    Next
    INDEX
    Explanations

    references to walls and related structures

    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
    protoimpl
    -0.64
    ----+
    -0.54
    mehr
    -0.52
    ælp
    -0.52
    inos
    -0.51
     المعيارى
    -0.51
    matic
    -0.50
    PRNewswire
    -0.49
    logy
    -0.49
    ualmente
    -0.49
    POSITIVE LOGITS
    PAPER
    0.68
    djangoproject
    0.67
    mounted
    0.61
    fahrts
    0.61
     mounted
    0.61
    covering
    0.61
    papers
    0.59
     Mounted
    0.57
     thickness
    0.54
     mount
    0.53
    Activations Density 0.167%

    No Known Activations