Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 12-GEMMASCOPE-RES-16K
    6. 4957
    Prev
    Next
    INDEX
    Explanations

    discussions about relationships, particularly in the context of personal and social dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aarrggbb
    -0.68
     fallu
    -0.58
    huk
    -0.58
    OrNil
    -0.56
     Leer
    -0.56
    htaccess
    -0.56
    espół
    -0.55
    ütün
    -0.54
     själv
    -0.54
    DebuggerNonUser
    -0.53
    POSITIVE LOGITS
     mutual
    0.69
    >{@
    0.59
    Mutual
    0.58
     estekak
    0.57
    NegativeButton
    0.53
    amic
    0.52
     Mutual
    0.52
    mutual
    0.51
    protoimpl
    0.51
     cordial
    0.50
    Activations Density 0.635%

    No Known Activations