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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15673
    Prev
    Next
    INDEX
    Explanations

    expressions of memory and connection to personal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    First-person perspective, past actions

    np_acts-logits-general · gemini-2.0-flash

    fond memories and admiration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.71
    лтемелер
    -0.65
     ligiloj
    -0.58
     <<<<<<<<<<<<<<
    -0.54
     CreateTagHelper
    -0.54
     lenker
    -0.52
     OMITBAD
    -0.52
    ercises
    -0.51
    batore
    -0.50
     Audiodateien
    -0.49
    POSITIVE LOGITS
     admiration
    0.82
     admired
    0.76
     admires
    0.75
     admire
    0.74
     friendship
    0.68
     respect
    0.67
     admiring
    0.66
     admirer
    0.61
     amizade
    0.60
     восхи
    0.58
    Activations Density 0.260%

    No Known Activations