© 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. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 986
    Prev
    Next
    INDEX
    Explanations

    references to military exercises and disasters

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1984
    +0.14
    0.5%
    776
    +0.13
    0.4%
    1804
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1984
    +0.14
    0.08
    16
    +0.13
    0.07
    1967
    +0.11
    0.04
    Negative Logits
     hâte
    -0.61
     gardien
    -0.55
    üyü
    -0.54
     compagni
    -0.53
     caratteri
    -0.53
     fidanz
    -0.51
    @[+][
    -0.51
     ILLUSTRATIONS
    -0.49
     consultato
    -0.49
     schonmal
    -0.49
    POSITIVE LOGITS
     maraming
    0.65
     Perci
    0.64
     jorge
    0.64
     Væ
    0.63
     santiago
    0.63
     Áng
    0.63
     Gå
    0.63
     bawat
    0.62
     getBase
    0.61
     ilang
    0.60
    Activations Density 0.469%

    No Known Activations