© 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. 1-GEMMASCOPE-RES-16K
    6. 3343
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "ini" and related terms, particularly in lists or contexts involving voting and stretching concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     trå
    -0.50
     zeitung
    -0.42
     pedas
    -0.41
     hemsida
    -0.41
     jorden
    -0.40
     onDestroy
    -0.39
     apsau
    -0.38
     biela
    -0.38
     dieną
    -0.38
     dormitórios
    -0.38
    POSITIVE LOGITS
    TypedDataSet
    0.71
     isolated
    0.69
    ini
    0.68
    bloc
    0.67
     Isolated
    0.66
    INI
    0.65
    isolated
    0.62
    fjspx
    0.62
    Isolated
    0.59
     noqa
    0.58
    Activations Density 0.321%

    No Known Activations