© 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
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 3477
    Prev
    Next
    INDEX
    Explanations

    names of locations, organizations, and political events

    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
    1842
    +0.14
    0.4%
    1499
    +0.13
    0.4%
    939
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    939
    +0.14
    0.06
    1499
    +0.13
    0.05
    124
    +0.12
    0.03
    Negative Logits
     intersper
    -1.27
     stickied
    -1.17
     fortn
    -1.16
     emphat
    -1.15
     encomp
    -1.15
     reluct
    -1.14
     impra
    -1.13
     !...
    -1.10
     ?...
    -1.10
     eyel
    -1.09
    POSITIVE LOGITS
     sovereignty
    0.63
     area
    0.56
     waters
    0.56
    vereignty
    0.55
    area
    0.53
    Area
    0.52
     exercises
    0.52
     areas
    0.52
     sovereign
    0.51
     territorial
    0.51
    Activations Density 0.327%

    No Known Activations