© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 5091
    Prev
    Next
    INDEX
    Explanations

    mentions of the letters 'ff' or phrases containing a significant number of 'f' characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    يكب
    -0.46
     transfieras
    -0.43
     AssemblyVersion
    -0.40
    igshid
    -0.40
    Organisateur
    -0.39
    lesias
    -0.39
    )_/¯
    -0.38
     censiti
    -0.38
     Administrativna
    -0.38
    tinyos
    -0.37
    POSITIVE LOGITS
    ff
    1.13
     ff
    0.93
    FF
    0.86
     FF
    0.84
     aff
    0.76
     Aff
    0.73
    Aff
    0.71
    iff
    0.69
    aff
    0.66
    ffs
    0.65
    Activations Density 1.261%

    No Known Activations