© 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-2-9B
    4. MLP Out - 131k
    5. 6-GEMMASCOPE-MLP-131K
    6. 110169
    Prev
    Next
    INDEX
    Explanations

    occurrences of the name "Ford."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-mlp/layer_6/width_131k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.6.hook_mlp_out
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ford
    -2.45
    FORD
    -2.27
    fords
    -1.47
     ford
    -1.38
    Ford
    -1.20
     FORD
    -1.09
     Ford
    -1.04
    фор
    -0.65
    fordshire
    -0.55
    フォ
    -0.54
    POSITIVE LOGITS
     مشين
    0.60
    yntaxException
    0.55
    GOTREF
    0.52
     OMITBAD
    0.49
    thâu
    0.46
    ductory
    0.46
     мәкал
    0.45
    SequentialGroup
    0.44
    WEBPACK
    0.43
     '\\;'
    0.43
    Activations Density 0.001%

    No Known Activations