© 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. 7601
    Prev
    Next
    INDEX
    Explanations

    information related to military actions, conflicts, and resistance

    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
    604
    +0.14
    0.4%
    1842
    +0.10
    0.3%
    736
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    736
    +0.14
    0.07
    1063
    +0.10
    0.04
    235
    +0.08
    0.05
    Negative Logits
     anse
    -1.00
     lele
    -0.97
     gesta
    -0.97
     frau
    -0.96
     utop
    -0.93
     makro
    -0.92
     praktik
    -0.92
    <bos>
    -0.92
     notor
    -0.91
     kram
    -0.89
    POSITIVE LOGITS
     outnumbered
    0.74
     formidable
    0.62
     overpowered
    0.61
     inferiority
    0.61
     overpowering
    0.61
     weakness
    0.60
     weakened
    0.58
     groupName
    0.58
     unprepared
    0.57
     defeat
    0.57
    Activations Density 0.765%

    No Known Activations